Localized Lora-Moe

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 20% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 62

Oct 1, 2026cs.AI

SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts

Spiking Neural Networks (SNNs) enable event-driven computation through biologically inspired dynamics at the neuronal scale, while Mixture-of-Experts (MoE) perform conditional computation through expert selection at the model scale. Integrating their strengths offers potential for flexible neural architectures. A key challenge, however, lies in designing an expert selection mechanism based on spiking activity. To address this, we introduce a spike-based k-WTA Router inspired by competition-inhibition observed in the hippocampal CA1 region. The router incorporates lateral inhibition and refractory period to select Top-K experts according to discrete spike counts. Building on this, we present SpikeMoE, a framework that integrates neuronal-scale spiking dynamics with model-scale expert selection. To address incomplete multisensory inputs in multimodal tasks, we further equip SpikeMoE with a two-stage missing-modality modeling module that combines empirical prototypes from an observed-modality pool with modality-specific learnable embeddings to construct missing-modality representations. Experiments on vision, language, and multimodal benchmarks demonstrate that SpikeMoE achieves state-of-the-art performance among the SNN baselines, matches or exceeds the performance of ANN counterparts, and maintains robustness across diverse missing-modality conditions. These results demonstrate a favorable trade-off between performance and energy efficiency, validating the integration of spiking dynamics with sparse expert computation and highlighting SpikeMoE as a promising approach to energy-efficient brain-inspired computing.

Xiaoli Liu, Yujie Liang, Jialin Li +1

School of Computer Science and Engineering, University of Electronic Science and Technology of China

Spiking Neural Networks Mixture-Of-Experts Architectures Mixture-Of-Experts Neuromorphic Computing Localized Lora-Moe

Oct 1, 2026cs.AI

ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models

Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs substantial computation and storage costs. Existing low-rank MoE compression methods largely rely on static factorization and fixed rank allocation, which overlook the distinctive properties of MoE DLMs. Specifically, we identify two properties: cross-mode non-uniform redundancy, where parameter redundancy and sensitivity to rank truncation vary across the input, output, and expert modes, and token-wise utilization variation, where hot and cold tokens exhibit distinct spectral characteristics and expert activation patterns. To address these challenges, we propose ITC-MoE, an Importance-guided Token-aware Compression framework for MoE DLMs. ITC-MoE consists of two complementary components. First, Importance-guided Adaptive Tucker Compression (IATC) incorporates activation and gradient importance into expert weight transformation, jointly factorizes expert weights across multiple modes, and adaptively allocates ranks under a fixed parameter budget. Second, Token-aware Compensation and Routing (TCR) applies lightweight low-rank compensation to compression-sensitive hot tokens and restricts the candidate expert set for cold tokens with concentrated routing patterns. By jointly adapting compression capacity and inference execution to both parameter redundancy and token-wise variation, ITC-MoE substantially reduces the computation and storage costs of MoE DLMs while preserving their generation quality. For example, on SDAR-30B-A3B-Chat-b32, ITC-MoE maintains an accuracy of 96.33% on MultiArith under a 30% compression budget, while achieving up to a 7.22x end-to-end speedup. The code is publicly available at https://github.com/lianjunl13-sudo/ITC-MoE.

Lianjun Liu, Shipeng Li, You Huang +5

Hainan University, Haikou, China · Xiamen University, Xiamen, China · Zhejiang Normal University, Jinhua, China

Token Compression Localized Lora-Moe Diffusion Language Models Experts

Sep 30, 2026cs.LG

Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization

While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive memory requirements. Extracting a compact subset of experts presents a promising solution. However, existing expert selection heuristics predominantly rely on Top-k ranking, which isolates the evaluation of individual experts and ignores the intricate inter-expert dependencies introduced by the MoE gating network. In this paper, we propose DS-MoE, a theoretically grounded framework that redefines expert selection via difference-of-submodular (DS) optimization. By analyzing the second-order Taylor expansion of the loss degradation, we reveal functional duality within expert combinations: redundancy (where experts encode overlapping representations) and synergy (where experts provide complementary error cancellation). To navigate this duality, we mathematically decouple redundancy reduction from synergy maximization by formulating the selection objective as a DS function. Furthermore, we devise a tailored majorization-minimization (MM) algorithm with provable monotonicity guarantees to efficiently identify the optimal expert subset. Extensive experiments demonstrate that DS-MoE effectively preserves indispensable expert combinations, achieving superior performance compared to the state-of-the-art baselines.

Zheng Lin, Shaoke Fang, Yuxin Zhang +6

Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg · Department of Computer Science, Peking University, China · Institute of Space Internet, Fudan University, China +4

Mixture-Of-Experts Localized Lora-Moe Submodular Functions Model Selection Redundancy Synergy

Sep 30, 2026cs.SD

UniAE-MoE: A Unified Audio Encoder via Mixture of Experts

Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder designed to model cross-domain audio representations and achieve outstanding downstream understanding performance via a Mixture-of-Experts (MoE) architecture. Specifically, we explore mainstream audio encoders and integrate those from Qwen2-Audio and Audio-Flamingo 3, which demonstrate superior downstream capabilities. To facilitate effective model fusion, we improve our encoder using SwiGLU with shared experts to decouple encoder networks, and we further introduce a two-stage instruction-tuning strategy to better adapt the model to diverse downstream tasks. Moreover, we propose the task-specific data scaling (TSDS) technique to enhance \tool's understanding capabilities. On the XARES-LLM benchmark, UniAE-MoE attains a score of 0.802, achieving state-of-the-art performance. It also delivers top-tier performance in the official Interspeech 2026 Audio Encoder Capability Challenge, further demonstrating robust generalization across diverse audio tasks. Together, these results validate the effectiveness of \tool for unified audio understanding across speech, music, and general audio domains.

Shengbo Cai, Zhisheng Zhang, Zichao Nie +3

Tsinghua University, China

Large Audio Language Models Opencode Encoders Localized Lora-Moe Experts Mixtures

Sep 29, 2026cs.CV

Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens independently within a homogeneous expert pool and regularizes expert usage toward uniformity, making it poorly matched to video data that is spatiotemporally redundant and semantically long-tailed. We show that existing visual MoEs fall into a uniformity trap: semantically under-organized routing, compounded by uniform expert-usage regularization, scatters coherent patches across disparate experts, causing routing fragmentation and structural distortion. To address this, we propose SplitMoE, a split-role sparse architecture that breaks the shackles of uniformity. To accommodate the inherent semantic imbalance, we explicitly bifurcate the expert pool into semantic experts and generic experts, with semantic experts capturing high-level semantic abstraction and generic experts preserving residual visual information and flexible generative capacity. Leveraging prototype-guided routing and pull-push regularization, SplitMoE enables tokens to cluster naturally by semantic attributes rather than arbitrary balancing constraints. Extensive results show that under an equivalent activated-parameter budget, SplitMoE outperforms traditional load-balanced MoEs in convergence speed, routing coherence, and video generation quality across standard benchmarks. By revealing an emergent coarse-to-fine denoising logic, SplitMoE provides the community with a modality-aware scaling path, serving as a critical reference for building large-scale video world models.

Yu Xu, Yuxin Zhang, Xiao Yang +7

University of Chinese Academy of Sciences · ByteDance · Canva Research +1

Video Diffusion Models Localized Lora-Moe Mixture-Of-Experts Video World Models

Sep 27, 2026cs.DC

OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading

Semi-autoregressive diffusion large language models (dLLMs) improve decoding parallelism through iterative block-wise denoising, but scaling them with mixture-of-experts (MoE) layers introduces a large expert parameter footprint that exceeds memory-constrained GPU capacity. Expert offloading is a natural remedy, yet existing MoE serving systems target autoregressive decoding and rely on intra-iteration layer-wise prefetching: while computing one layer, they predict and load experts for subsequent layers. Under dLLM inference, block-wise routing expands the active expert working set within each iteration, making such prefetches difficult to complete in time and costly when mispredicted. Consequently, existing prefetch-based solutions often degenerate into on-demand expert loading with high decoding latency. We propose OLED-MoE, an expert offloading system that shifts the optimization target from intra-iteration prefetching to inter-iteration expert retention. Its key insight is that adjacent denoising iterations exhibit strong expert routing overlap, and token confidence indicates which experts are likely to be reused. OLED-MoE uses confidence-guided inter-iteration prediction to retain high-value experts in GPU memory without introducing extra prefetch traffic. It further compensates unavoidable cache misses through CPU-GPU cooperative execution, jointly considering dynamic expert computation load and predicted future reuse. Across diverse dLLM workloads, OLED-MoE reduces time per output token (TPOT) by 1.23x-7.93x and improves expert cache utilization by 1.44x-4.23x over state-of-the-art offloading systems. Notably, OLED-MoE approaches full-residency performance while using only 40% of the expert GPU memory, incurring merely 23% higher TPOT despite a 60% reduction in expert memory footprint. OLED-MoE's source code is publicly available at https://github.com/flashserve/OLED-MoE.

Jingyuan Xiao, Jiayue Wang, Yitao Hu +7

Tianjin University, Tianjin, China · Tianjin University Tianjin, China

Mixture-Of-Expert Inference Offloading LLM Inference Optimization Localized Lora-Moe Preemption Graphics Processing Unit Memory+1

Sep 22, 2026cs.MA

Calibration Is Not Verification: Falsifiability-Aware Conformal Routing for Mixture-of-Agents

Multi-agent language systems often treat agreement as evidence, yet heterogeneous agents can jointly repeat an unsupported claim or omit a correct specialist fact. We introduce C-MoA, an agreement-based conformal filter that turns inter-agent semantic support into a claim-level nonconformity score and calibrates a retention threshold at the example level, giving distribution-free within-domain factuality control for heterogeneous Mixture-of-Agents. C-MoA is effective: it nearly doubles retained-claim precision on long-form generation (from 0.41 to 0.75), certifies a human-labelled medical set, and transfers across domains without recalibration; its one failure mode is short-form answering, where consensus is cheap and the score is left near chance. We then ask whether counterfactual falsifiability can push past consensus, and introduce CONTRA-MoA, which adds a blinded near-miss tournament, leave-one-agent-out stability, and availability-aware fusion. This extension helps only where the verifier holds domain knowledge, dropping half of the false medical claims at 0.940 precision, whereas with a memory-only judge the added signals are near chance (AUC 0.531 and 0.511) and naive max fusion degrades the working agreement signal from 0.687 to 0.652. The message is twofold: agreement-based conformal calibration delivers reliable, transferable factuality control, while moving beyond consensus requires a knowledgeable verifier, availability-aware signals, and robust fusion.

Nada Rahali, Zijia Wang, Zhisong Liu

LUT University, Finland · Dell Technologies, United Kingdom · Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom

Mixture-Of-Agents Facts Localized Lora-Moe

Sep 21, 2026cs.CV

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages and the difficulty of serving diverse scripts within a single model. Existing solutions either deploy one recognizer per language, inflating cost and introducing error accumulation, or rely on massive vision-language models (VLMs) that are expensive and still inaccurate on many scripts. In this work, we pursue an all-in-one multilingual recognizer that is simpler than per-language experts, lighter than VLMs, and more accurate than both. First, we construct TextMuSS-10M, a large-scale synthetic scene text dataset spanning 10 scripts and 229 languages. It provides balanced and sufficient supervision where real data is unavailable. Second, we propose ScriptMoE, a script-aware Mixture-of-Experts (MoE) architecture. It shares a single visual encoder and replaces the dense decoder with a sparse MoE block, which consists of an image-level router dispatches each image to the top-2 script-aligned experts and a shared expert absorbs cross-script knowledge. Extensive experiments on our assembled TextMuSS-Bench (10 scripts, 10,899 images) show that ScriptMoE achieves the highest accuracy of 82.06%, outperforming the strongest STR baseline by 1.31%. On the CC-OCR end-to-end multilingual task, replacing only the recognizer in PP-OCRv5 with ScriptMoE lifts F1 score from 65.71% to 80.89%, slightly surpassing the best VLM (80.73%) at a fraction of the parameter count.

Xingsong Ye, Yongkun Du, Jiaxin Zhang +6

Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI · WeChat Vision, Tencent Inc. +1

Scene Text Recognition Lingdt-Vl-Ocr Recent Vision-Language Models Localized Lora-Moe Mixture-Of-Experts Text Analysis and Detection

Sep 14, 2026cs.AI

STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecasting

Spatio-temporal traffic forecasting is a fundamental big data analytics task for intelligent transportation systems, where massive urban sensor streams exhibit heterogeneous, non-stationary, and structurally dynamic patterns. Although recent deep learning and large language model (LLM)-based methods have advanced traffic forecasting, they often remain temporally centered and lack effective coordination of temporal, spectral, pairwise spatial, and higher-order structural cues under evolving traffic regimes. To address this heterogeneous dependency coordination problem, we propose STHMoE, a Spatio-Temporal Hypergraph-Enhanced Mixture of Experts framework for urban traffic data forecasting. STHMoE decouples traffic dynamics into frequency-domain, time-domain, spatio-domain, and higher-order spatial representations, which are modeled by prompt-guided heterogeneous experts built upon a partially frozen LLM backbone. The first three experts leverage domain-specific statistical prompts, while the higher-order spatio expert uses a structural placeholder prompt and obtains dependency information from an adaptive hypergraph module. To capture evolving spatial structures in traffic data,, STHMoE jointly learns first-order graph dependencies and higher-order group interactions without predefined topologies. An entropy-aware MoE router with coefficient-of-variation load balancing adaptively fuses expert outputs while improving expert utilization and routing confidence. Experiments on 10 real-world traffic benchmarks show that STHMoE achieves competitive performance against temporal, spatio-temporal graph, and LLM-based baselines.

Jiawen Chen, Qi Shao, Yongjian Chang +3

School of Mathematics, Southeast University, Nanjing 210096, China · School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China · Jiangsu Province Center for Applied Mathematical Sciences, Nanjing 210096, China

Accurate Traffic Forecasting Localized Lora-Moe Graph Neural Networks

Sep 9, 2026cs.LG

OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit

Mixture-of-Experts (MoE) models enable efficient scaling of large language models but face critical deployment challenges due to massive memory requirements. Existing pruning methods either incur prohibitive search costs or neglect the dynamic interdependencies between experts. To address these challenges, we present OMP-MoE, a novel training-free compression framework for reducing expert redundancy in MoE-based LLMs. Based on observations of expert contribution patterns, we reformulate the pruning problem as a sparse signal reconstruction task solved through Orthogonal Matching Pursuit. Specifically, our method first treats individual expert contributions as dictionary atoms and selects experts that greedily minimize reconstruction error with linear computational complexity. Then, we optimize cross-layer expert allocation through a water-filling strategy that accounts for both reconstruction quality and routing stability. Finally, we introduce OMP-MoE†, an adaptive inference mechanism that dynamically adjusts expert activation based on energy prediction. Comprehensive experiments on Qwen, DeepSeek-V2, GPT-OSS, and Mixtral MoE demonstrate consistent improvements over existing methods at 25-50% pruning ratios. For Qwen3-30B-A3B at 50% compression, we retain 93.3% of original performance, achieving 33

\times

faster search and 1.55

\times

inference speedup. Codes will be available after acceptance.

Dezhi Li, Lujun Li, Qiyuan Zhu +4

The Hong Kong University of Science and Technology

Mixture-Of-Experts Large Language Models Large Language Model Compression Localized Lora-Moe Experts

Sep 1, 2026cs.CL

Instella-MoE Technical Report

In this work, we introduce Instella-MoE, a fully open Mixture-of-Experts (MoE) language model with 16 billion total parameters and 2.8 billion active parameters per token, trained entirely from scratch on AMD Instinct MI300X and MI325X GPUs. Instella-MoE combines a sparsely activated MoE design with architectural and system-level innovations, including Gated Multi-head Latent Attention (Gated MLA) and FarSkip-Collective connectivity, enabling efficient large-scale training and inference. The model is developed through a multi-stage pipeline comprising pre-training, mid-training, long-context extension, supervised fine-tuning with feedback-driven data curation, direct preference optimization, and reinforcement learning with Multi-Teacher On-Policy Distillation. Instella-MoE achieves an average score of 76.7 across standard pre-training benchmarks, outperforming prior fully open models including OLMo-3-7B, SmolLM3-3B, and OLMoE-1B-7B, while remaining competitive with open-weight MoE and dense baselines at comparable active-parameter scales, including Moonlight-16B-A3B and Qwen3.5-4B. After post-training, our final Think checkpoint achieves an average score of 73.2 across instruction-following, reasoning, math, coding, and chat benchmarks, outperforming both fully open and open-weight models with comparable or larger active parameter counts in our evaluation. To support transparent and reproducible research, we release the complete Instella-MoE model flow, including model weights, training configurations, data mixtures, and training code. Together, these contributions establish Instella-MoE a strong, fully open foundation for efficient, high-performing MoE models and reproducible research.

Jiang Liu, Sudhanshu Ranjan, Prakamya Mishra +10

Localized Lora-Moe Mixture-Of-Experts Technical Report Report

Aug 15, 2026cs.CV

DCA-MoE: Spatially Adaptive Cross-Layer Fusion and Density-Routed Experts for Crowd Counting

Crowd counting must recover reliable local density under severe variations in perspective, head scale, occlusion, and background clutter. Although modern counting objectives provide strong spatial supervision, many multi-level decoders still use spatially invariant feature fusion and apply one receptive-field pattern to every location. We propose DCA-MoE, a framework that makes both decisions content dependent while retaining a frozen DINOv3 encoder. Spatially Adaptive Layer Fusion (SALF) predicts position-wise weights over four aligned backbone features, and Density-Routed Multi-Receptive-Field Experts (DR-MoE) assigns each location a soft mixture of local, mid-range, and large-context residual experts. An EBC-style head reconstructs block density, while DMCount supervision and an auxiliary routing-balance term train the decoder without updating the backbone. On the NWPU-Crowd validation split, the strongest paired configuration, based on DINOv3 ViT-L/16, obtains 31.7 MAE and 72.2 RMSE; the matched ViT-B/16 full model obtains a paired 32.2/75.9. Cross-dataset results remain mixed, and several component baselines currently report independently selected minima from a single seed. The evidence therefore supports the feasibility of spatially adaptive fusion and routing, while broader paired and multi-seed evaluation remains necessary for causal attribution.

Hao Wang

BDNRC

Spatial Supervision Localized Lora-Moe Experts Objectives

Aug 13, 2026cs.SD

HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement

Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics, and Schrödinger Bridges (SB) shorten transport from noise to clean speech but leave inference cost only loosely tied to training. We propose HybridSB-MoE, a dual-domain framework that fills these gaps through three contributions unified by a single asymmetric design principle. (i) Asymmetric uncertainty fusion: The spectral path captures epistemic uncertainty via expert disagreement, while the waveform bridge models aleatoric variance through stochastic dynamics. We fuse them asymmetrically, allowing the mixing weight to adapt to distinct error regimes rather than average predictions. (ii) Heterogeneous MoE with top-k=2 routing across five distinct architectural archetypes, where architectural diversity makes the epistemic signal indicate which inductive bias fails rather than small perturbations among similar experts. (iii) Discretization bound (Theorem 1): path-consistency and trajectory regularizers together bound the K-step bridge sampling error in 2-Wasserstein distance at rate K-alpha, making small-K inference an objective-level guarantee rather than an empirical claim. On VoiceBank+DEMAND, HybridSB-MoE outperforms diffusion- and SB-based baselines at their step budgets while remaining competitive with consistency-distilled few-step methods.

Zhengyi Lu, Aswini Sivakumar, Jie Hu +1

Department of Computer Science and Engineering, Oakland University, Rochester, MI 48309

Speech Enhancement Schrödinger Bridges Speech Synthesis Localized Lora-Moe Waveforms Spectral+1

Aug 10, 2026cs.CV

DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning

Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centralized data access and costly joint training. This is restrictive when data is distributed across private, domain-specific, or permission-limited clients. To this end, we propose DistMoE, a mixture-of-experts (MoE) approach for distributed visual instruction tuning. In each layer of the language decoder it augments the public feedforward network (FFN) with a client-specific private FFN expert, with the goal to acquire domain-specific knowledge. However, independent expert training causes the private FFNs to learn representation of different scale and magnitudes, making merging the experts difficult. To reduce client-specific drift, we introduce a public-anchored expert composition stage that updates only routers and lightweight private projection adapters on a mix of local client data and public data, via an isotropic regularization loss, therefore making it cross-client rehearsal-free composition. During inference, DistMoE performs modular routing over public and private experts, enabling token-wise domain composition without explicit domain labels. Experiments across diverse visual-language benchmarks show that DistMoE enables flexible expert reuse, effective domain adaptation, and competitive performance while preserving modular control over client-specific knowledge. Codes are available at https://github.com/mainaksingha01/DistMoE.

Mainak Singha, Niccolò Biondi, Elisa Ricci +1

University of Trento, Italy · Fondazione Bruno Kessler, Italy · University of Bergamo, Italy

Multimodal Continual Instruction Tuning Mixture-Of-Experts Instruction Tuning Multimodal Large Language Models Vision-Language Model Adaptation Localized Lora-Moe+2

Aug 4, 2026cs.LG

AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding

Speculative decoding verifies a tree of draft tokens in one target-model forward pass. For a mixture-of-experts (MoE) target, however, parallel verification can activate the union of the experts selected by all tree nodes, even though only a small subset of those nodes reaches the accepted output. Token count, activated-expert union size, and expert-weight traffic are therefore distinct cost measures: reducing the token workload need not shrink the expert union proportionally, and under offloading, transfer traffic also depends on cache residency. We introduce AcceptMoE, a verifier-side expert selector that combines target-router scores with offline-estimated commitment probabilities and automatically adjusts the number of eligible experts for each verification block, eliminating the need for a user-specified expert budget. Under offloading, AcceptMoE conditions expert eligibility on cache residency instead of predicting natural routes and prefetching the corresponding expert weights. Although constraining target-expert eligibility changes the model distribution, across 12 model-task pairs spanning three MoE targets and four benchmarks, AcceptMoE's mean accuracy is 0.27 percentage points lower than that of EAGLE-3 speculative decoding with natural routing. Served with SGLang at batch size one, it reaches 1.290 times the throughput of this baseline with all expert weights in GPU memory, and 2.06 times under physical expert offloading, while reducing host-to-device traffic by 73.6 percent to 77.1 percent.

Shuang Liang, Hao Mark Chen, Zhiwen Mo +4

Imperial College London · Tile-AI

Mixture-Of-Expert Inference Localized Lora-Moe Speculative Decoding

Aug 3, 2026cs.CV

ReMiX-MAE: Learning Missing-Channel Cross-Modal Representations from RGB-Only Clinical Facial Videos for Sympathetic-Mediated Pain Assessment

Automated pain assessment in real clinics is limited by scarce clinically grounded facial video data with weak labels (often sequence-level self-report) and by the fact that pain cues can be subtle or near-neutral in RGB, while thermal and depth signals are informative yet impractical to deploy routinely. To address these challenges, we propose ReMiX-MAE (Reconstructing Missing Channel Cross-Modal Masked Autoencoder), a self-supervised multimodal masked pretraining framework that learns transferable facial representations from synchronized RGB, thermal, and depth videos and explicitly trains robustness to missing modalities, enabling RGB-only deployment. To fill the gap of clinically grounded facial pain data with video-level self-report and longitudinal treatment trajectories, we collect the Sympathetic Mediated Pain (SMP) dataset with paired pre- and post-recordings across multiple visits. Under RGB-only deployment, we evaluate ReMiX-MAE using both direct feature extraction and pseudo-multimodal features decoded from RGB. ReMiX-MAE consistently outperforms an RGB-only masked autoencoder baseline on SMP, with pseudo-multimodal features providing additional gains in the challenging five-class setting. Across external datasets, ReMiX-MAE further shows more robust and label-efficient transfer than RGB-only baselines, highlighting its advantage in data-limited clinical settings.

Nan Bi, Taoyue Wang, Lijun Yin +1

School of Computing, Binghamton University, Binghamton, NY, USA · Department of Anesthesiology, SUNY Upstate Medical University, Syracuse, NY, USA

3D Masked Autoencoders Facial Expression Recognition Cross-Modal Localized Lora-Moe

Jul 29, 2026cs.LG

TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification

The promise of multimodal fusion lies in combining complementary sources of evidence, yet more evidence does not always yield a better prediction. Recent multimodal models have advanced fusion through richer cross-modal interaction and sample-adaptive fusion. However, the influence assigned to a modality during fusion does not reveal whether that source is unreliable, redundant, or poorly matched to a specialized expert. To address this limitation, we introduce TIER-MoE, a risk-guided subspace mixture-of-experts model that defines sample-specific modality reliability as the prediction loss its unimodal predictor is expected to incur. This risk is learned from out-of-fold predictions generated by models that were not trained on the corresponding sample. TIER-MoE combines the estimated risk with expert-specific subspace compatibility for sparse modality-expert routing, while an always-active shared path preserves multimodal complementarity. We evaluate TIER-MoE on four public multimodal biomedical datasets spanning Alzheimer's disease status, skin-lesion malignancy, and retinal classification. Results demonstrate its superiority over state-of-the-art methods in predictive performance and probability calibration, with consistent improvements in Macro-F1 and Brier score and strong zero-shot generalization to an external cohort.

Yu Chang, Anzhe Cheng, Chenwei Wu +7

University of Southern California · University of Michigan · 3The University of British Columbia +1

Multimodal Fusion Unimodal Metrics Localized Lora-Moe

Jul 29, 2026cs.HC

Sensor-Placement-Agnostic Sonomyography: Toward Continuous High-Dimensional Control by Users with Tetraplegia

Sonomyography (SMG) enables continuous device control via ultrasound-measured muscle deformation signals, but existing SMG interfaces generally require substantial user- and sensor-location-specific training data and provide only one proportional signal or task-specific classification. We present a real-time, sensor-placement-agnostic SMG control system based on sparse optical flow tracking that enables continuous 1-DOF control after minimal calibration (3 pose definitions). We also present a preliminary expansion of this method that augments this algorithm with a short computer-aided calibration to enable 2-DOF control. We evaluate both 1- and 2-DOF systems' performance for a preliminary cohort of 3 cervical spinal cord injury survivors and 6 uninjured individuals across 6 sensor placements spanning the arm, neck, and upper torso. As assessed by a cursor trajectory tracking task, all participants achieved continuous 1-DOF control at all tested sensor locations (even those that relied on passive tissue motions), with all participants achieving <5.5% tracking error using at least one placement (and many <4% across many). All participants were also able to modulate 2D cursor position via the 2-DOF system, with varying levels of control authority, and several were able to complete a 2D drawing task, constituting the first (to our knowledge) demonstration of location-agnostic multi-DOF continuous SMG-based control. These results highlight the promise of SMG to enable rapidly calibratable, high-dimensional, sensor-placement-agnostic device control by users with tetraplegia, and also illuminate key challenges in both signal processing and practical system deployment. To enable further development by scientific and user communities, developed algorithms have been open-sourced as part of the OpenMyoControl project on SimTK (simtk.org/projects/openmyocontrol).

Gavin Sueltz, Vikram Athithan, Emma Ferran +3

Departments of Mechanical Engineering and Physical Medicine & Rehabilitation, the Kahlert School of Computing, and the Robotics Center at the University of Utah, Salt Lake City, UT 84112, USA

Robust Control Localized Lora-Moe

Jul 27, 2026cs.CV

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design

Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows. AIGC Foundation Models (AFMs), especially diffusion-transformer backbones, have begun to adopt sparse experts, but recent efforts mostly enlarge total parameter counts and sparsity ratios without importing the efficiency mechanisms that made LLM scaling practical, so generation quality is seldom balanced against training and deployment cost. This raises a natural question: can the architectural principles behind efficient LLM scaling be adapted to AFMs in a more balanced way? We introduce ModernMOE (MMOE), a modernization of SiT-style diffusion transformers that systematically adapts routed experts, shared and lightweight experts, gate-residual routing, and attention-residual information reuse to AIGC generation. Rather than treating MoE as a single plug-in replacement, MMOE studies how different modern expert components affect convergence, efficiency, and generation quality when composed inside a diffusion transformer. Every experiment in this paper is trained on a single eight-GPU H100 node with batch size 256 for 400k steps, an accessible single-machine budget. Under matched training and sampling protocols and at this budget, MMOE reaches lower FID at every recorded checkpoint, that is, it converges faster per training step, than dense and intermediate sparse-expert baselines, and among the sparse variants it attains the best quality-cost balance. Routing analysis further shows stable expert specialization across depth, substantial use of lightweight routes, and modest step-to-step routing changes during denoising. These results suggest that AFMs can follow the balanced scaling path of LLMs by importing proven efficiency designs, rather than by simply increasing total parameters and sparsity ratios.

Yanhao Jia, Jiepeng Wang, Haibin Huang +3

College of Computing and Data Science, Nanyang Technological University, Singapore, 639798 · Institute of Artificial Intelligence of China Telecom (TeleAI), Shanghai, China, 200232

Localized Lora-Moe Diffusion Transformers Wireless Foundation Models

Jul 7, 2026cs.CV

SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts

Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry. Existing 3D-aware models either rely on costly 3D-specific data or utilize RGB-only inputs with heuristic sampling and monolithic, shallow fusion, which respectively disrupt essential spatiotemporal connectivity and induce modality contention across diverse spatial tasks. To overcome these bottlenecks, we introduce SpaR3D-MoE, an end-to-end framework that enables adaptive spatial reasoning by equipping MLLMs with geometry-aware capabilities from only sparse RGB inputs. First, we propose an adaptive spatiotemporal manifold sampling mechanism that constructs a geometry-aware spatiotemporal graph to extract informative keyframes, effectively mitigating sequence redundancy while preserving the scene's topological connectivity. Second, we introduce the heterogeneous geometry-inductive Mixture-of-Experts driven by an instruction-pose aware router, which adaptively routes multimodal tokens to specialized experts, resolving the cross-modal contention inherent in monolithic fusion. Extensive experiments on VSI-Bench, ScanQA, and SQA3D demonstrate that our method achieves state-of-the-art performance. Notably, SpaR3D-MoE achieves the highest average score of 63.5 on VSI-Bench, outperforming the strongest baseline by 7.8 absolute points, alongside relative improvements of 35.4% and 51.4% in Route Plan and Relative Direction tasks, respectively.

Haida Feng, Hao Wei, Haolin Wang +3

State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, China · YUKUN Intelligent World, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, China

3D Spatial Reasoning Spatial Reasoning Multimodal Large Language Models Mixture-Of-Experts Localized Lora-Moe

Jul 6, 2026cs.LG

Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse operational contexts. However, standard methods like LoRA are structurally limited by a monolithic bottleneck, making them highly susceptible to gradient warfare. Interleaved multi-task streams may trigger destructive optimization feedback, collapsing adapter weights into unspecialized averages. While recent spatial partitioning methods have introduced block-wise isolation, they remain trapped in static topologies, unable to adapt to dynamic task-switching or environmental sensor failure. In this work, we introduce Localized LoRA-MoE, a unified framework that fuses localized spatial blocking with dynamic, context-conditioned routing. We propose and evaluate two novel architectural paradigms: Block-Wise LoRA-MoE (Centralized Macro-Routing), which modulates the entire structural grid via a monolithic context signal, and Cell-Wise LoRA-MoE (Decentralized Micro-Routing), which empowers every coordinate cell in the matrix grid with autonomous, localized expert gating. Through a comprehensive suite of benchmarks, ranging from high-dimensional SVD matrix simulations and real-world tabular transformations to spatial vision perception under sensor degradation, we demonstrate that both architectures resolve optimization deadlocks inherent in static baselines. Our empirical results establish that decentralized cell-level gating achieves complete statistical parity with an omniscient global coordinator, providing a robust "gradient firewall" that protects surviving pathways from fault-propagated corruption. Our proposals consistently outperform static baselines, offering a scalable and parameter-efficient solution for dynamic model adaptation across granular coordinate fields and shifting operational regimes.

Babak Barazandeh, Subhabrata Majumdar, Vinay Prithyani +1

Fortinet · Indian Institute of Management Bangalore · Citadel Securities +1

Layer-Wise Localized Lora-Moe Gating Experts War

Jul 5, 2026cs.CL

WPG-MoE: Weak-Prior-Guided Dense Mixture-of-Experts for User-Level Social Media Depression Detection

Online social media posts provide scalable signals for early depression screening, and recent studies mainly improve pre-classification evidence through risk-post selection, symptom grounding, and clinically informed feature construction. However, these screening-stage designs often leave final decisions to a single detector, overlooking how users heterogeneously express depressive risk after screening. A monolithic classifier must average across heterogeneous users, which may dilute localized evidence and cause misclassification, especially for non-self-disclosing users. To address this issue, we propose WPG-MoE, a weak-prior-guided dense mixture-of-experts framework built on a shared large language model (LLM) backbone. WPG-MoE derives user-level weak semantic priors to softly route users to experts matched to different evidence layouts. We formulate this process as learning using privileged information (LUPI): rich LLM-extracted structured evidence guides training-time routing, while inference retains only Patient Health Questionnaire-9 (PHQ-9) template screening and the deployable backbone. Experiments on Chinese and English datasets show that WPG-MoE outperforms strong baselines with interpretable routing behavior.

Xian Li, Yuanhe Tian, Yang Yang +2

University of Electronic Science and Technology of China · Zhongguancun Academy · University of Science and Technology of China

Depression Screening Localized Lora-Moe

Jun 28, 2026cs.RO

MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments

Robust robot autonomy depends on scene representations that remain stable enough to support localization, navigation, and downstream decision making in dynamic environments. Monocular Gaussian Splatting SLAM provides high-fidelity mapping, but current uncertainty-aware methods still treat dynamic regions largely as per-frame observations. This makes the representation effectively memoryless: when a pedestrian slows, pauses, or reappears after occlusion, the current frame may look static, allowing dynamic content to be absorbed into the map and leaving persistent ghosting artifacts. We argue that this failure reflects a representation-level mismatch. Dynamic-ness is not an instantaneous appearance property, but a temporal property defined by motion history. Building on this view, we introduce Motion Permanence: the principle that an object's dynamic identity should persist over time rather than be re-decided from each frame independently. We realize this principle in MoPe, a memory-aware uncertainty filter for monocular Gaussian mapping. MoPe propagates the historical dynamic posterior through geometry-consistent SE(3) warping and fuses it with current-frame evidence using bounded Bayesian log-odds updates. The resulting persistent posterior guides tracking, mapping, dynamic-aware Gaussian insertion, and Gaussian-level post-cleanup. On Wild-SLAM, Bonn, and TUM sequences, MoPe improves tracking robustness and reduces residual ghosting, with the strongest gains on dynamic-human scenes that most directly violate the memoryless assumption. These results show that maintaining temporal dynamic state inside the scene representation is a practical step toward more reliable representation-centric autonomy in changing real-world environments.

Qixin Xiao

University of Michigan

Gaussian Splatting Simultaneous Localization And Mapping Systems Motion-Based Perception Dynamic Environments Persistence Uncertainty-Aware Classification Localized Lora-Moe

Jun 26, 2026cs.CV

CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection

We present CLEAR-MoE, a four-phase post-training pipeline that converts a frozen pretrained Vision Transformer (ViT) into a sparse Mixture-of-Experts (MoE) model without updating backbone weights. The pipeline (i) scores feed-forward network (FFN) layers by sparsity, clusterability, and output sensitivity; (ii) decomposes selected layers into a shared low-rank SVD basis and per-cluster residual experts using k-means clustering; (iii) trains lightweight routers supervised by cluster labels; and (iv) dispatches tokens through pluggable CUDA backends. On Imagenette with DeiT-Small, CLEAR-MoE retains 99.9% of the dense model's accuracy (86.70 +/- 0.02% versus 86.73%). Extensive ablation studies reveal a consistent empirical finding: the shared SVD basis is the primary factor responsible for preserving accuracy. Random routing, learned routing, and three different router architectures produce nearly identical performance, with accuracy varying by at most 0.06 percentage points (86.62%-86.68%). Accuracy also remains stable across different SVD ranks, expert counts (2-8), calibration set sizes (50-500), and random seeds. This behavior generalizes across five ViT backbones (DeiT-Tiny, DeiT-Small, DeiT-Base, ViT-Small, and ViT-Base), covering models from 5.7M to 86.6M parameters, with accuracy differences <= 0.10 percentage points from their dense counterparts. On a GTX 960 GPU, routing and scatter-gather overhead make the CLEAR-MoE FFN 1.3-1.7x slower than the dense implementation. A dispatch microbenchmark further shows that routing is an order of magnitude more memory-bound than expert matrix multiplications, identifying fused dispatch kernels as a promising direction for future optimization.

Md Irtiza Hossain, Humaira Ayesha, Junaid Ahmed Sifat

Brac University

Vision Transformer Localized Lora-Moe Frozen Vision-Language Models Experts Feed-Forward

Jun 25, 2026cs.CV

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have focused on adaptively allocating computational resources across diverse tokens to improve efficiency and performance. However, we identify a routing assignment problem in existing diffusion MoE frameworks: the router fails to accurately allocate more computational resources to salient tokens. Our analysis attributes this failure to the router's reliance on noise-corrupted latent features throughout the denoising process. Such stochastic noise obscures the critical structural and textural information, thereby preventing the router from effectively distinguishing salient tokens. To address this, we propose SharpMoE, a post-training framework with a saliency-harnessing accurate routing mechanism, which utilizes clean latent features as a noise-free guidance signal for routing. By bypassing the noise-distorted inputs, SharpMoE provides the router with clear saliency guidance, enabling the identification of salient tokens even in high-noise stages. Furthermore, we introduce a trajectory routing loss to constrain the compute allocation throughout the multi-step denoising trajectory, ensuring precise resource allocation along the generation rollout. Extensive experiments demonstrate that SharpMoE serves as a versatile, plug-and-play solution that further enhances the pretrained, converged MoE models, achieving state-of-the-art performance in visual generation.

Haoyou Deng, Keyu Yan, Chaojie Mao +4

Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology · Tongyi Lab, Alibaba Group

Localized Lora-Moe Mixture-Of-Experts Noise-Aware

Jun 23, 2026cs.AI

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sustain gains as depth increases, exhibiting degradation, early plateauing, or saturation. We propose ReM-MoA, a memory-augmented MoA framework that sustains scaling through two mechanisms: (1) a Ranked Reasoning Memory that persistently stores and ranks reasoning traces from all layers using a comparative Reviewer Agent, and (2) a Curated Diversified Memory Routing scheme that exposes different agents to distinct combinations of successful and failed traces, preserving exploration diversity while propagating high-quality reasoning. We further introduce an optional multi-domain Reviewer distillation pipeline that improves ranking quality through frontier-model supervision. Across five reasoning benchmarks spanning math, formal logic, code, knowledge, and commonsense, ReM-MoA consistently outperforms prior MoA variants across both depth and width scaling, and its advantage widens with depth, establishing structured cross-layer reasoning memory as a key missing mechanism for scalable multi-agent inference.

Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +5

University of Southern California · Iowa State University · Cisco AI Research

Mixture-Of-Agents Localized Lora-Moe Scaling Reviewer

Jun 21, 2026cs.LG

Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search

We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via itertools.combinations, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at https://github.com/ABrain-One/nn-gpt

Yashkumar R Lukhi, Harsh Rameshbhai Moradiya, Radu Timofte +1

Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany

Mixture-Of-Experts Neural Architecture Search Localized Lora-Moe Exploration

Jun 19, 2026cs.PF

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference. Each token activates only a small subset of experts, so the per-token compute cost, in floating-point operations (FLOPs), resembles that of a much smaller dense model. Whether that FLOP advantage survives in practice is far less clear. We ask whether MoE models actually run faster and cheaper than comparable dense models on consumer-grade and edge hardware. We benchmark OLMoE-1B-7B (1.3 B active of 6.9 B total) against three dense baselines on an Apple M2 Pro and an NVIDIA Jetson Orin Nano 8 GB through llama

.

cpp, measuring throughput, memory, and on-device energy. The answer is device-dependent: OLMoE's active-parameter advantage is only partly realised on the laptop (~10% behind the same-active Llama-3.2-1B) and erodes on the edge device (~31% behind, at 2.1

\times

the energy per token, with peak memory at the 8 GB ceiling). Patching llama

.

cpp to time the decode graph node-by-node shows routing accounts for under 9% of MoE-block compute on the cleaner edge backend, so the gap reflects total-parameter memory footprint, expert dispatch, and KV-cache pressure rather than routing. The implication is that on bandwidth-bound edge hardware, inference cost tracks total parameters, not active ones, and sparse activation does not buy back what the device is constrained on. These findings are bounded to one MoE model at this parameter scale and two devices, and we release the full measurement harness and per-run data.

Alfarizy Alfarizy, Hung Truong Thanh Nguyen, René Richard +2

Analytics Everywhere Lab, University of New Brunswick, Fredericton, NB, Canada · TSAI Lab, University of New Brunswick, Fredericton, NB, Canada

Mixture-Of-Expert Inference Mixture-Of-Experts Localized Lora-Moe Inference Cost Edge Hardware Peak Memory+2

Jun 17, 2026cs.RO

CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion

Perceptive legged locomotion over discontinuous terrain (e.g., stairs, gaps, and obstacles) requires adaptive behavior, as a single conservative gait cannot produce the anticipatory maneuvers needed for abrupt topology changes. Cast as multi-task reinforcement learning, this problem introduces a tension between sharing and separation. Tasks use a common locomotion base but have conflicting rewards, so a policy must share behavior while avoiding value interference. Prior work addresses only one side, with monolithic policies sacrificing specialization and hierarchical sub-policies sacrificing generalization across transitions and unseen terrain. We propose CTS-MoE, which combines a dense mixture-of-experts actor with perception-based gating to compose shared behaviors and a multi-critic with task-specific value heads to prevent interference. The model is trained end-to-end in a single-stage concurrent teacher-student setup that handles partial observability and avoids sequential distillation, with task labels used only during training. At deployment, routing depends solely on perception, allowing terrain adaptation without a high-level selector or terrain classifier. Experiments on a Unitree Go1 in simulation and on hardware across seen and unseen terrains show task-aware specialization, with lower tracking error and higher success rates than monolithic baselines. Project Website: https://cts-moe.github.io/ .

Francisco Affonso, Matheus P. Angarola, Ana Luiza Mineiro +3

University of Illinois Urbana-Champaign · University of São Paulo

Agile Locomotion Terrain Localized Lora-Moe Multi-Turn Reinforcement Learning Mixture-Of-Experts

Jun 15, 2026cs.CV

DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis

Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI). Yet, early identification remains challenging due to the complex structural and functional alterations it induces in the brain. To address this, we propose a dynamic multimodal Mixture-of-Experts (MoE) framework that integrates functional and structural connectivity through time-aware functional-structural encoding and class-conditioned expert routing. Within this framework, modality-specific and cross-modal experts learn complementary representations, while a Modality-Class MoE (MCoE) module dynamically adjusts expert weights according to each classification objective. Experimental results across three binary classification tasks demonstrate that the framework consistently outperforms static fusion baselines, and high-interpretability analyses further reveal meaningful regions of interest (ROIs) interactions. This dynamic multimodal expert framework effectively captures class-dependent brain interaction patterns and provides an interpretable approach for PTE diagnosis and risk stratification.

Jun-En Ding, Spencer Chen, Henry Noren +6

Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ, USA · Department of Systems Engineering, Stevens Institute of Technology, Hoboken, NJ, USA

Seizure Detection Human Brain Networks Brain Tumor Classification Localized Lora-Moe

Jun 12, 2026cs.RO

Safe Reinforcement Learning of Autonomous Highway Driving: A Unified Framework for Safety and Efficiency

Deep reinforcement learning (DRL) offers a compelling route to decision-making for advanced autonomous vehicles (AVs), yet its trial-and-error nature makes it difficult to guarantee safety during training and to achieve both safety and efficiency at deployment. We propose a unified safe reinforcement learning (SRL) framework that integrates safe distance (SD), reward machines (RM), and mixture-of-experts (MoE), termed MoE-RM-SRL. For deployment, SD and RM jointly shape a rule-aware reward that encodes highway traffic regulations and stage-wise objectives, enabling safe and reliable behavior without sacrificing efficiency. For training, we introduce a sparsely gated MoE layer comprising up to 11 deep Q-networks (DQNs); an SD-based gating rule activates a minimal set of experts for lane-keeping and lane-changing, mitigating the instability, discontinuities, and impulsive transients commonly induced by switching between heterogeneous controllers (e.g., MPC/rule-based modules and learned policies). We implement the proposed architecture in CARLA and integrate it with a 6-DoF driver-in-the-loop virtual-reality (DiL-VR) platform. Experiments in stochastic two-lane traffic show that MoE-RM-SRL substantially improves safety and efficiency over state-of-the-art baselines, and the framework naturally extends to multi-lane driving as well as on-ramp merging and exiting scenarios.

Chufei Yan, Zhihao Cui, Yiyan Lv +3

School of Physics, Northeast Normal University, Changchun, 130024, China. · 2Clean Energy Automotive Engineering Center, School of Automotive Studies, Tongji University, Shanghai, 201804, China. · 3Mengshi Automobile Technology Company, Dongfeng Motor Corporation, Wuhan, 430010, China.

Automated Vehicles Offline Reinforcement Learning Unified Framework Localized Lora-Moe

Jun 3, 2026cs.RO

CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation

Humans primarily rely on walking and running to traverse complex terrains. Similarly, humanoid robots should be able to smoothly transition between walking and running while maintaining natural and stable locomotion. However, unifying gait transition and multi-terrain adaptation within a single policy remains challenging due to gradient interference between tasks and the distribution shift caused by terrain variations. Although Mixture-of-Experts (MoE) architectures can mitigate multi-skill interference, direct joint training often fails to achieve clear expert specialization. To address these challenges, we propose CoRe-MoE, a two-stage reinforcement learning framework that decouples gait generation from terrain adaptation. In the first stage, a stable locomotion policy is learned to produce natural walking and running behaviors with smooth transitions. In the second stage, a terrain-aware MoE branch is introduced, and the gating network is trained with a contrastive objective to learn structured terrain representations and promote expert specialization. The final action is obtained through weighted fusion of the base gait policy and the terrain-aware branch, enabling the policy to preserve stable locomotion while adapting to complex terrains. Extensive simulation results demonstrate that the proposed method outperforms baseline approaches in terms of success rate, locomotion stability, and multi-terrain adaptability. Furthermore, zero-shot deployment on a Unitree G1 humanoid robot validates the effectiveness of our framework, achieving robust walking and running across stairs, slopes, steps, obstacles, and unstructured outdoor terrains while maintaining accurate foothold control and dynamic stability.

Kailun Huang, Zikang Xie, Yanzhe Xie +8

Hong Kong University of Science and Technology · Hong Kong University of Science and Technology (Guangzhou) · Guangdong University of Technology +3

Agile Locomotion Gait Dynamics Full-Body Humanoid Control Localized Lora-Moe Experts Contrastive Learning

Jun 3, 2026cs.LG

LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling

Mixture-of-Experts (MoE) and looped architectures scale models along two orthogonal axes, namely parameter capacity and effective depth. However, mainstream looped architectures rely on dense backbones that couple parameter count with per-token FLOPs, which makes it impossible to isolate the effect of iterative computation under matched budgets. To this end, we present LoopMoE, a looped MoE language model that integrates sparse routing with iterative weight-shared computation through two designs. The first is IterAdaLN, which resolves weight-sharing symmetry via a modulation signal jointly conditioned on the iteration index and the per-token hidden state. The second is a capacity-balancing strategy that recovers the attention-to-FFN active parameter ratio of well-tuned non-looped references. Together, these designs enable the first strictly controlled, head-to-head evaluation of a looped MoE against a Vanilla MoE under identical total parameters, per-token FLOPs, and active sublayer ratios. At the 3B scale, LoopMoE outperforms the Vanilla MoE on 8 of 9 downstream benchmarks with an average improvement exceeding 1 point. At the 9B scale, LoopMoE continues to outperform the matched Vanilla MoE, indicating that the architectural gain persists at larger scale. Our work establishes a controlled synthesis of sparsity and recurrence, and suggests a promising direction for looped language models.

Wenkai Chen, Tianshu Li, Wenyong Huang +3

Hong Kong University of Science and Technology (Guangzhou) · Huawei Technologies Co.,Ltd.

Mixture-Of-Experts Large Language Models Mixture-Of-Experts Localized Lora-Moe Iterative

Jun 1, 2026cs.LG

DOT-MoE: Differentiable Optimal Transport for MoEfication

The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While Mixture of Experts (MoEs) architectures address this by decoupling model size from inference cost, training MoEs from scratch is often unstable and compute intensive. Conversion of pre-trained dense models into sparse MoEs has emerged as an alternative solution; however, existing methods typically rely on heuristic neuron clustering or random splitting to partition the Feed-Forward Network (FFN) into experts. In this work, we propose DOT-MoE, a novel framework that formulates the decomposition of dense layers as a Differentiable Optimal Transport (DOT) problem. Instead of static heuristics, we model neuron assignment as a balanced transport problem, utilizing differentiable Sinkhorn-Knopp iterations to enforce strict expert capacity constraints. Furthermore, we utilize Straight-Through Estimators (STE) to jointly learn the discrete neuron-to-expert assignment and the token-to-expert routing policy end-to-end. Extensive experiments across multiple architectures and benchmarks demonstrate that DOT-MoE significantly outperforms structured pruning, heuristic clustering, and random-split baselines, retaining 90% of the original dense model's performance while reducing active parameters by 50%.

Udbhav Bamba, Arnav Chavan, Aryamaan Thakur +2

Amazon

Localized Lora-Moe Inference Cost Differentiable Optimal Transport

May 31, 2026cs.AI

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge. Prior work shows that fine-grained experts enlarge the space of expert combinations and improve flexibility, but they also impose substantial routing overhead, creating a new scalability bottleneck. In this paper, we explore a complementary axis for scaling -- how expert outputs are aggregated. We theoretically show that replacing the standard weighted-summation aggregation with structural aggregation expands the expert-combination space without altering the experts or router, and enables possible multi-step reasoning within a single MoE layer. To this end, we propose DAG-MoE, a sparse MoE framework that employs a lightweight module to automatically learn the optimal aggregation structure among the selected experts. Extensive experiments under standard language modeling settings show that DAG-MoE consistently improves performance in both pretraining and fine-tuning, surpassing traditional MoE baselines.

Jiarui Feng, Hanqing Zeng, Karish Grover +11

Meta MRS · Washington University in St. Louis · Carnegie Mellon University +1

Mixture-Of-Experts Architectures Mixture-Of-Experts Localized Lora-Moe

May 30, 2026cs.CV

MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts

Bounding-box regression is a fundamental component of object detection, playing a critical role in precise object localization. Existing Intersection-over-Union (IoU)-based loss functions extend the IoU objective by incorporating geometric penalties, such as center-distance and aspect-ratio mismatch, to improve bounding-box regression. However, these penalties typically remain fixed throughout training and do not account for the optimization dynamics in which predicted boxes initially exhibit large center-distance and shape errors, with later stages focusing on improving overlap with the ground truth. To address this limitation, we introduce MoEIoU, a mixture-of-experts based regression loss that jointly models overlap, center alignment, and aspect-ratio mismatch. MoEIoU aggregates these components using a log-sum-exp function, which emphasizes the dominant localization error while maintaining smooth contributions from other terms. Additionally, a curriculum-based weighting schedule is employed to prioritize correcting box position and shape in early training stages and improving overlap in later stages. We evaluated proposed MoEIoU on PASCAL VOC, HRIPCB, and MS COCO using multiple YOLO architectures, along with large-scale simulation experiments. It consistently outperforms standard and recent state-of-the-art losses, demonstrating faster convergence and improved localization accuracy. We further show that this adaptive aggregation improves existing IoU-based losses, yielding consistent gains and providing more effective optimization guidance for bounding-box regression in object detection frameworks.

Vinay Edula, Priyanka Bagade

Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur, U.P, India

Bounding Box Object Detection Object Localization Loss Function Localized Lora-Moe Experts+1

May 29, 2026eess.IV

MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstruction

Undersampled magnetic resonance imaging (MRI) reconstruction seeks to recover temporally or contrast-varying image series from incomplete multicoil k-space data while preserving state-dependent fidelity for dynamic and quantitative MRI (qMRI). Existing scan-specific implicit neural representations (INRs) often use monolithic spatiotemporal coordinate fields, explicit subspaces, motion or deformation models, calibration variables, or sequence-specific quantitative signal models. These design choices can limit flexibility in sharing spatial information while adapting image synthesis across acquisition states. Moreover, many INR-based baselines remain computationally demanding, typically requiring per-scan optimization times on the order of hundreds to thousands of seconds. We propose MoE-dqINR, a scan-specific multicoil MRI reconstruction framework that factorizes the image-domain representation into shared spatial experts and a state-conditioned routing pathway. Spatial experts encode reusable coordinate-dependent image content, whereas routing weights, conditioned on ordered acquisition states, synthesize each dynamic frame or contrast state from a common expert bank. The representation is coupled to a multicoil MRI forward model, uses the normalized state index to drive routing in both dynamic and quantitative MRI. By separating shared spatial representation from state-dependent synthesis, the framework provides an image-first architecture for dynamic and quantitative MRI while reducing scan-specific INR optimization to approximately 30 s per scan in our experiments. The proposed formulation establishes state-conditioned mixture-of-experts INR as a scan-specific multicoil MRI reconstruction prior that unifies shared spatial representation, dynamic- and qMRI-specific synthesis, and practical per-scan efficiency.

Yinzhe Wu, Fanwen Wang, Zhenxuan Zhang +3

Department of Bioengineering and I-X, Imperial College London, London, SW7 2AZ, United Kingdom · Cardiovascular Research Centre, Royal Brompton Hospital, London, SW3 6NP, United Kingdom · Shanghai Pudong Hospital and Human Phenome Institute, Fudan University, Shanghai, China +3

Magnetic Resonance Imaging Reconstruction Magnetic Resonance Imaging Neural Representations Localized Lora-Moe

May 29, 2026cs.CL

dMoE: dLLMs with Learnable Block Experts

Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive models, offering competitive performance while naturally supporting parallel decoding. However, as dLLMs are increasingly integrated with Mixture-of-Experts (MoE) architectures to scale model capacity, a fundamental mismatch arises between block parallel decoding and token-level expert selection. Specifically, each dLLM forward pass processes multiple tokens with bidirectional dependencies, whereas conventional MoE layers route each token independently. This mismatch substantially increases the number of uniquely activated experts, making inference increasingly memory-bound. To address this, we propose dMoE, a simple yet effective block-level MoE framework. The central idea of dMoE is to aggregate token-level expert distributions within each block into a unified block-level expert distribution, which is then used to guide expert routing in a more coherent manner. In this way, dMoE substantially reduces the number of uniquely activated experts during inference without sacrificing performance, thereby mitigating the memory-bound bottleneck. Extensive experiments across a variety of benchmarks demonstrate the effectiveness of dMoE. On average, dMoE reduces the number of uniquely activated experts from 69.5 to 14.6 while retaining 99.11% of the original performance. Meanwhile, it reduces memory usage by 76.64% to 79.84% and achieves 1.14

\times

to 1.66

\times

end-to-end latency speedup. Code is available at: https://github.com/fscdc/dMoE

Sicheng Feng, Zigeng Chen, Gongfan Fang +2

National University of Singapore

Mixture-Of-Experts Localized Lora-Moe Diffusion Language Models Experts

May 28, 2026cs.LG

Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting

Spatio-temporal forecasting on sensor graphs is commonly tackled with a single backbone architecture applied uniformly across all nodes, although graph regions can exhibit different dynamics. Road segments differ in functional class, structure, and traffic behavior, suggesting that node-wise expert specialization can be useful. We propose GC-MoE, a graph-conditioned mixture of experts framework that assigns each node a personalized combination of frozen forecasting experts based on graph topology and the recent traffic input window. GC-MoE combines frozen pretrained spatio-temporal GNN experts with an input-aware, spatially contextualized router while training only a lightweight routing module. We also study a bounded graph-conditioned output refinement layer as an optional extension and include node-adaptive ST-LoRA adapters only as an ablation diagnostic. Across four standard benchmarks (PEMS04, PEMS07, METR-LA, and PEMS-BAY), GC-MoE improves MAE over a zero-parameter ensemble baseline, with competitive RMSE and MAPE, while training only ~17K parameters on top of 1.5M frozen expert weights. The implementation is available at https://github.com/Ahghaffari/gc_moe.

Amirhossein Ghaffari, Saeid Sheikhi, Ekaterina Gilman

Future Computing Group, University of Oulu

Accurate Traffic Forecasting Temporal Graph Neural Networks Localized Lora-Moe Sensors

May 28, 2026cs.LG

MōLe-Λ: Learning the Coupled-Cluster Response State for Energies, Gradients, and Properties

Coupled-cluster (CC) theory is often considered the gold standard of quantum chemistry, but its high computational cost limits routine access to accurate energies, forces and response properties. While the right-hand

T

-amplitudes determine the correlated wavefunction, many practically important observables additionally require the left-hand

Λ

-amplitudes. We introduce MōLe-

Λ

, an extension of Molecular Orbital Learning (MōLe) that predicts the full ground-state coupled-cluster singles and doubles (CCSD) response state by jointly learning right-hand amplitudes

(T_1,T_2)

and left-hand amplitudes

(Λ_1,Λ_2)

from localized Hartree--Fock molecular orbitals. Architecturally, MōLe-

Λ

extends MōLe with

Λ_1

and

Λ_2

readouts that mirror the symmetry constraints of the

T_1

and

T_2

heads, while preserving the original equivariant orbital encoder, odd sign-equivariant decoding, locality and size-extensivity. The resulting model yields accurate CC-quality energies and forces, while simultaneously recovering dipoles, quadrupoles, polarizabilities, the electron density, and 2-electron observables such as the pair density. We show that MōLe-

Λ

further extends the speed advantage of MōLe over full CCSD while substantially expanding the accessible properties, providing a route to wavefunction-level surrogate models for correlated quantum chemistry.

Andreas Burger, Luca Thiede, Abdulrahman Aldossary +4

University of Toronto, Canada · Vector Institute for Artificial Intelligence, Toronto, Canada · NVIDIA, Toronto, Canada +2

Quantum Chemistry Density Functional Theory Localized Lora-Moe Surrogate Models Gradient

May 28, 2026cs.AI

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training compression methods mainly shrink this cost by pruning experts or merging their weights. We formulate post-training MoE compression as expert-pool consolidation: retaining a smaller set of pretrained experts as reusable prototypes and deterministically remapping each original expert reference to one selected prototype. This view separates the reduced expert pool from the reuse structure that represents the original expert slots, and allows prototype sharing within local layer scopes while preserving the original router interface. We propose ConMoE, a train-free prototype remapping framework that selects retained experts using calibration-based contribution and replaceability signals, then redirects original expert calls to the selected prototypes without weight updates or post-compression fine-tuning. Experiments on three pretrained MoE language models show that ConMoE matches or outperforms strong pruning and merging baselines in several settings, achieving the best average score on deepseek-moe-16b-base at both 25% and 50% routed-expert reduction, while remaining competitive on Qwen3-30B-A3B and OLMoE-1B-7B-0125. Ablations indicate that deterministic reassignment is the most stable component, whereas broader cross-layer sharing and post-hoc weight fusion are model-dependent.

Yilun Yao, Jiaming Pan, Elsie Dai +3

Peking University

Mixture-Of-Experts Large Language Models Mixture-Of-Experts Localized Lora-Moe

May 27, 2026cs.CL

Pruning and Distilling Mixture-of-Experts into Dense Language Models

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for memory-constrained deployment. Existing compression methods reduce the number of experts but the output remains an MoE model with the same fundamental limitation. We present the first systematic framework for converting a trained MoE into a standard fully dense architecture: experts are scored, selected, and grouped, then concatenated into a dense FFN and refined by knowledge distillation from the MoE teacher. We evaluate 7 scoring, 5 grouping, and 2 magnitude scaling methods across a range of selected expert counts on Qwen3-30B-A3B, yielding 350 configurations. We find that the choice of scoring method is the most impactful, with our novel diversity-aware scoring consistently outperforming prior methods on Qwen3-30B-A3B, DeepSeek-V2-Lite, and GPT-OSS-20B. Under a controlled comparison at matched parameter count, MoE-to-dense outperforms dense-to-dense pruning by +6.3 pp in average downstream accuracy after ~4B-token distillation at 1.6x faster training wall-clock speed.

Junhyuck Kim, Jihun Yun, Haechan Kim +3

1KRAFTON · 2KAIST

Mixture-Of-Experts Large Language Models Mixture-Of-Experts Localized Lora-Moe Large Language Model Compression Knowledge Distillation

May 26, 2026cs.LG

MobileMoE: Scaling On-Device Mixture of Experts

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present MobileMoE, a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier for on-device LLMs. We first formulate an on-device MoE scaling law that jointly optimizes MoE architecture under mobile memory and compute constraints, identifying an on-device sweet spot - moderate sparsity with fine-grained and shared experts - that is simultaneously memory and compute-optimal. Building on the derived architectures, we train MobileMoE with a four-stage recipe covering pre-training, mid-training, instruction fine-tuning, and quantization-aware training, all on open-source datasets. Across 14 benchmarks, MobileMoE matches or exceeds leading on-device dense LLMs with 2-4

\times

fewer inference FLOPs, and matches or surpasses the state-of-the-art MoE OLMoE-1B-7B with up to 60% fewer parameters. To bridge the last mile to mobile deployment, we provide the first efficient MoE inference on commodity smartphones with comprehensive on-device profiling. At comparable INT4 weight memory, MobileMoE-S delivers

1.8

-

3.8\times

faster prefill and

2.2

-

3.4\times

faster decode than the dense baseline MobileLLM-Pro.

Yanbei Chen, Hanxian Huang, Ernie Chang +5

Meta AI

Mixture-Of-Experts Large Language Models Mixture-Of-Expert Inference Localized Lora-Moe

May 25, 2026cs.CV

BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is biologically heterogeneous, shaped by the interplay between hepatic functional reserve and tumor-related oncologic factors; thus, similar survival outcomes may reflect fundamentally different underlying biological processes. Prognostic modeling in HCC is informed by rich multimodal information from multiparametric MRI and radiology reports from routine clinical practice. Existing prognostic vision-language models (VLMs) learn a single entangled latent representation that blends hepatic and tumor-related factors, limiting both accuracy and biological interpretability. We present BioFact-MoE, a biologically factorized Mixture of Experts (MoE) framework that explicitly decomposes liver and tumor factors via biologically supervised experts within a residual MoE survival architecture. On a HCC cohort of N=588 patients (pretrained on 4,582 3D MRI image-report pairs), BioFact-MoE consistently improves survival prediction over all baselines across time horizons, achieving 12-, 18-, and 24-month AUCs of 75.33%, 75.85%, and 73.96%. Beyond scalar risk prediction, gated expert weights enable phenotype-aware risk stratification. Pathway-informed gating uncovers clinically meaningful treatment-associated survival heterogeneity. In held-out validation, hepatic and tumor embeddings show selective associations with liver function and tumor burden markers, respectively (p<0.05), without supervision. The code is available at https://github.com/jy-639/BioFact-MoE.

Junlin Yang, Tian Yu, Nicha C. Dvornek +6

Department of Radiology & Biomedical Imaging, Yale University, New Haven, CT, 06510, USA · Department of Biomedical Engineering, Yale University, New Haven, CT, 06510, USA · Department of Electrical Engineering, Yale University, New Haven, CT, 06510, USA +1

Cholangiocarcinoma Experts Localized Lora-Moe Recent Vision-Language Models Factor Behavioral Embeddings

May 24, 2026cs.LG

Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization

We apply the influence-adaptive Walsh geometry of a companion theory paper (arXiv:2605.01637) to extreme low-bit weight-only LLM quantization. The recipe is one math-invariant transformation: WHT-rotate each linear layer's weight matrix and rescale its columns by per-coordinate Walsh-basis activation energy before handing off to a reconstruction-error quantizer (Intel auto-round). This biases per-group integer rounding toward high-spectral-energy channels. On four pretrained decoder-only models from 135M to 1.5B parameters, BBT-spectral reduces wikitext-2 perplexity by 15-58% relative to vanilla auto-round at W2A16; we also report a TinyLlama-1.1B auxiliary data point. Three extensions transfer the recipe to families it failed on: a per-head PCA matrix-Gamma replacement of q_norm/k_norm for Qwen3 attention (PPL 136.76 -> 88.99 on Qwen3-0.6B); an SO(2) per-pair rotation that commutes with RoPE (PPL 36.93 -> 21.84 on Qwen2.5-1.5B); and an MoE-aware input-side absorption fix identified by architectural fuzzing of Laguna-style fused-expert layouts. A W2-vs-W4 ablation gives a deliberate negative control: the redistribution payoff falls within the +/-0.5 PPL noise floor at W4, consistent with the Schur-convexity intuition that the cost of unconcentrated influence vanishes as the noise budget shrinks. All quantized weights export to OpenVINO IR and run on Intel NPU + Arc dGPU + CPU with PPL invariant to device within +/-0.1. We do not claim a formal Boolean-to-real-valued transfer of the theory paper's majorization argument: the WHT activation energy used here is not the Boolean influence of the theory paper, the link is intuitive, and the contribution is engineering value rather than a transferred theorem. Head-to-head benchmarks against SpinQuant, QuaRot, QuIP-sharp, AQLM, OmniQuant, and ButterflyQuant at matched calibration are the main future-work item.

Gorgi Pavlov

Lehigh University

Large Language Model Quantization Model Weights Spectral Free-Energy Landscape Localized Lora-Moe

May 23, 2026cs.CL

Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs

Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter interference. To address these issues, we propose Mix-MoE, a mixed Mixture-of-Experts framework designed to train LLMs for multilingual MT. Our framework operates in two distinct stages: (1) post-pretraining with MoE on monolingual corpora, and (2) post-pretraining with MoE on parallel corpora. Crucially, we divide the MoE layers into two specialized groups: Language Model Experts (LM Experts) and Machine Translation Experts (MT Experts). LM Experts are designed to capture and retain the monolingual knowledge learned by the pre-trained LLM. MT Experts, on the other hand, are specifically trained to acquire and store bilingual translation knowledge. Furthermore, to facilitate effective interaction between these specialized experts and leverage potential underlying structural patterns in text, we introduce a routing mechanism enhanced by Fourier Transform features derived from model representations. The experimental results demonstrate that Mix-MoE excels in multilingual MT, significantly outperforming existing baselines and showing notable progress in mitigating parameter interference.

Bo Li, Tianyu Dong, Shaolin Zhu +1

School of Software, Tsinghua University · College of Intelligence and Computing, Tianjin University

Multilingual Language Models Mixture-Of-Experts Large Language Models Localized Lora-Moe Language Model Computes Text Corpora

May 22, 2026cs.LG

BitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization

Mixture-of-Experts (MoE) large language models incur substantial memory costs due to their large expert parameter counts. Mixed-precision quantization reduces these costs by allocating different bit-widths to experts or linear blocks according to their importance. However, assigning a single precision within each expert or linear block overlooks its internal structural heterogeneity. This limitation motivates two key questions: (1) how to define a fine-grained unit for quantization within a linear transformation; and (2) how to characterize the quantization cost of each unit under actual activation patterns and different bit-widths. To address these two questions, we propose BitsMoE, a cost-aware mixed-precision quantization framework built on two complementary techniques: (1) Shared-basis Spectral Decomposition (SSD) separates expert weights into a shared basis and expert-specific spectral components, defining structural quantization units while exploiting cross-expert redundancy. (2) Factorized Quantization Cost Modeling (FQCM) estimates component-wise costs from output reconstruction loss by combining intrinsic spectral importance, activation-dependent importance, and bit-width-dependent distortion. Using these component-wise costs, we formulate bit allocation as an integer linear program (ILP) that minimizes total modeled quantization cost under a fixed memory budget. On Qwen3-30B-A3B at 2-bit, BitsMoE achieves 64.29% average accuracy over seven downstream tasks, outperforming the evaluated MoE-specific methods, including those using ILP-based bit allocation, and exceeding GEMQ by 2.80 percentage points. Under the same setting, it achieves a

16.47\times

end-to-end offline quantization speedup over GEMQ. It also achieves up to

6.46\times

the decode throughput of GPTQ.

Jiayu Zhao, Zihan Teng, Minhao Fan +4

School of Microelectronics, University of Science and Technology of China · College of Computing and Data Science, Nanyang Technological University · School of Electrical and Electronic Engineering, Nanyang Technological University

Large Language Model Quantization Localized Lora-Moe Spectral

May 22, 2026cs.NE

SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks

Spiking Neural Networks (SNNs) provide an energy-efficient paradigm for visual recognition. We present SpikingMoE, which integrates a spike-driven Transformer with a Mixture-of-Experts (MoE) framework for dynamic computation. Inspired by the lateral geniculate nucleus (LGN), a spike-driven prompt (SDprompt) enables input-dependent expert routing in a biologically plausible manner. By replacing standard MLPs with spike-compatible expert modules and enforcing binary spike communication, SpikingMoE is designed for neuromorphic hardware. Experiments on CIFAR-10 and CIFAR-100 achieve 94.09% and 74.54% top-1 accuracy, showing that modular expert routing can be incorporated while retaining reasonable performance. To our knowledge, SpikingMoE is the first open-source SNN framework that integrates MoE into a spike-driven Transformer with LGN-inspired routing.

Yukai Yang, Chenxi Qin, Jungang Li +3

Tianjin University, Medical School, Tianjin 300072, China · Southern University of Science and Technology, Department of Computer Science and Engineering, Shenzhen, Guangdong 518055, China · Chinese Academy of Medical Sciences, Institute of Biomedical Engineering, Tianjin 300192, China

Spiking Neural Networks Neuromorphic Computing Localized Lora-Moe Neural Network

May 18, 2026cs.LG

CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing LoRA-based MoE continual learning methods still face a fundamental trade-off: they either isolate experts too aggressively, limiting knowledge transfer across tasks, or allow task-specific updates to overwrite important existing parameters, leading to severe forgetting. To address this, we propose CP-MoE, a continual learning framework built around a transient expert that captures early task-specific updates and guides their integration into stable experts. CP-MoE introduces a consistency-preserving routing bias, which uses the transient expert to estimate representation similarity with stable experts and steer routing towards more compatible expert selection, and a transient expert-guided regularisation mechanism, which selectively protects important historical parameters during merging. Together, these components reduce parameter interference and forgetting while preserving cross-task knowledge transfer. We validate CP-MoE on both unimodal and multimodal continual learning benchmarks with LLM-based and VLM-based MoE models. On SuperNI benchmark, spanning diverse sequential language tasks, CP-MoE achieves state-of-the-art performance and stronger zero-shot transfer to unseen tasks. On VQA v2 dataset, it scales effectively to multimodal visual reasoning, consistently reduces forgetting, and outperforms strong MoE baselines.

Yang Liu, Toan Nguyen, Flora D. Salim

School of Computer Science and Engineering University of New South Wales Australia

Replay-Based Continual Learning Mixture-Of-Experts Large Language Models Catastrophic Forgetting Continual Learning Mixture-Of-Experts Localized Lora-Moe

May 18, 2026cs.LG

CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution

The Mixture-of-Experts (MoE) architecture improves computational efficiency via sparse expert activation, but throughput-oriented inference faces substantial GPU memory pressure due to a significant parameter size and intermediate data. Prior works attempt to mitigate this using expert offloading with micro-batching or by offloading computation to the CPU. However, the fragmented workload resulting from micro-batching degrades operational intensity, causing expert execution to become memory-bound. Meanwhile, CPU offloading is constrained by slow PCIe transfers and its limited applicability to attention computation in the decode stage. Consequently, these inefficiencies prevent effective system utilization, severely restricting the end-to-end throughput of MoE inference. To address these challenges, this paper proposes CoX-MoE, an Advanced Matrix Extensions (AMX)-enabled CPU-GPU collaborative system that comprehensively optimizes MoE inference by combining coalesced expert execution with strategic workload orchestration for higher throughput. CoX-MoE introduces (i) a coalescing-aware orchestration policy to jointly optimize resource allocation by adopting ordinary batch, instead of micro-batch, for expert computation and selective attention offloading, and (ii) a static expert-aware stratification scheme that pre-assigns frequently activated experts to the GPU, mitigating PCIe transfer overhead and balancing workload for the CPU and GPU during inference. Compared to state-of-the-art frameworks, CoX-MoE delivers significant gains, achieving up to 7.1x and 2.4x higher throughput than FlexGen and MoE-Lightning, respectively.

Muyoung Son, Yi Chen, Seungjae Yoo +2

KAIST · Daejeon, Republic of Korea

Mixture-Of-Expert Inference Mixture-Of-Experts Cpu-Gpu Hybrid Designs Localized Lora-Moe

May 18, 2026cs.CV

Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation

CNN- and Transformer-based architectures have achieved strong performance in medical image segmentation, but CNNs are limited in modeling long-range dependencies, while Transformers often suffer from quadratic computational and memory complexity. State space models, especially Mamba-based networks, offer an efficient alternative with linear sequence complexity. However, existing Mamba segmentation models still face two limitations: pixel-wise directional scanning can disrupt local 2D spatial structure, and simple summation-based fusion of scan directions cannot adapt well to diverse object sizes, shapes, and boundaries. To address these issues, we propose \textit{Patch-MoE Mamba}, a patch-ordered mixture-of-experts state space architecture for medical image segmentation. It introduces a hierarchical patch-ordered scanning mechanism that preserves local spatial neighborhoods while capturing multi-scale context, and an MoE-based directional fusion module that adaptively combines multiple Mamba scanner outputs using four directional experts, a learnable concatenation expert, and residual directional aggregation. Experiments on five public polyp segmentation benchmarks and the ISIC 2017/2018 skin lesion segmentation datasets demonstrate the effectiveness and generality of Patch-MoE Mamba.

Diego Adame, Fabian Vazquez, Jose A. Nunez +7

University of Texas Rio Grande Valley, Edinburg, TX 78539, USA

Semi-Supervised Medical Image Segmentation Cnn-Transformer Tradeoff Convolutional Neural Networks Mixture-Of-Experts Localized Lora-Moe

May 14, 2026cs.LG

Eradicating Negative Transfer in Multi-Physics Foundation Models via Sparse Mixture-of-Experts Routing

Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of disparate partial differential equation (PDE) regimes can induce gradient conflict, unstable optimization, and plasticity loss in dense neural operators. In particular, broadband open-channel fluid dynamics and boundary-dominated porous media flows impose incompatible spectral and geometric demands on a single dense parameter path. We introduce Shodh-MoE, a sparse-activated latent transformer architecture for multi-physics transport. Shodh-MoE operates on compressed 16^3 physical latents produced by a physics-informed autoencoder with an intra-tokenizer Helmholtz-style velocity parameterization, restricting decoded states to divergence-free velocity manifolds. The model guarantees exact mass conservation, achieving a physically verifiable velocity divergence of ~2.8 x 10^-10 (evaluated post-hoc in FP64) on 128^3 grids. A Top-1 soft-semantic router dynamically assigns localized latent patches to expert subnetworks, enabling specialized parameter paths for distinct physical mechanisms while preserving shared experts for universal symmetries. In a 20,000-step distributed pretraining run over mixed three-dimensional physical tensors, routing telemetry shows autonomous domain bifurcation: held-out validation tokens from the open-channel domain route exclusively to Expert 0, while porous-media tokens route exclusively to Expert 1. The model converges simultaneously across both regimes, achieving latent validation MSEs of 2.46 x 10^-5 and 9.76 x 10^-6, and decoded physical MSEs of 2.48 x 10^-6 and 1.76 x 10^-6. These results support sparse expert routing as a practical architectural mechanism for mitigating multi-physics interference in universal neural operators.

Ellwil Sharma, Arastu Sharma

Shodh AI

Latent Transport Wireless Foundation Models Localized Lora-Moe Foundation Model

May 9, 2026cs.LG

Sparse Layers are Critical to Scaling Looped Language Models

Looped language models repeat a set of transformer layers through depth, reducing memory costs and providing natural early-exit points at loop boundaries. However, looped models do not scale as favorably as standard transformers with unique layers. We compare standard and Mixture-of-Experts (MoE) transformers, with and without looping, and find two main results. First, we find Looped-MoE models scale better than the standard baseline while dense looped models do not. We trace this to routing divergence between loops: in Looped-MoE models, different experts are activated on each pass through the same shared layers, recovering expressivity without additional parameters. Our second finding is that looped models have better compute-quality trade-offs with early exits than standard models. Because each loop ends with the same layers that produce the final output, loop boundaries are superior exit points, as confirmed by earlier output convergence at these points. In sum, we provide a clear direction for scaling looped models: a Looped-MoE model with early exits can not only beat standard transformers at scale, but also enable significant memory and inference savings with minimal degradation in quality.

Ryan Lee, Jacob Biloki, Edward J. Hu +1

1USC Information Sciences Institute · 2Netflix · 3Independent Researcher

Transformer Architectures Layer-Wise Localized Lora-Moe Mixture-Of-Experts Peak Memory

May 4, 2026cs.CV

Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE

We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the model's generation capability, we equip the Diffusion Transformer backbone with a fine-grained Mixture-of-Experts (MoE) design (128 experts, Top-8 routing), yielding a 25B-parameter model that activates only 3B parameters, significantly reducing training costs while scaling up the model capacity. Mamoda2.5 achieves top-tier generation performance on VBench 2.0 and sets a new record in video editing quality, surpassing evaluated open-source models and matching the performance of current top-tier proprietary models, including the Kling O1 on OpenVE-Bench. Furthermore, we introduce a joint few-step distillation and reinforcement learning framework that compresses the 30-step editing model into a 4-step model and greatly accelerates model inference. Compared to open-source baselines, Mamoda2.5 achieves up to

95.9\times

faster video editing inference. In real-world applications, Mamoda2.5 has been successfully deployed for content moderation and creative restoration tasks in advertising scenarios, achieving a 98% success rate in internal advertising video editing scenario.

Yangming Shi, Shixiang Zhu, Tao Shen +14

Mamoda Team, ByteDance

Diffusion Models Multimodal Understanding Localized Lora-Moe

May 3, 2026cs.LG

MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving

Production LLM workloads increasingly serve discriminative tasks, such as classification, recommendation, and verification, whose answers are read from the logits of a single prefill pass with no autoregressive decoding. Serving these prefill-only workloads on mixture-of-experts (MoE) models is bottlenecked not by compute but by the distributed execution required to fit the model: existing parallel strategies (tensor, expert, and pipeline parallelism) trade memory pressure for redundant computation, communication, and synchronization, severely degrading MoE prefill serving efficiency. We observe that these overheads stem from coupling expert placement with synchronous activation routing -- a design inherited from the decoding era. The long, compute-bound forward passes of large-batch prefill open a per-layer window wide enough to stream expert weights in the background, replacing per-layer activation AllToAll with asynchronous weight AllGather fully overlapped with computation. We propose MoE-Prefill, a prefill-only serving system whose backend, AsyncEP (Asynchronous Expert Parallelism), gathers experts by weight rather than routing them by activation, and whose frontend co-enforces a physically-derived saturation threshold through prefix-aware routing and true-FLOPs load tracking. On Qwen3-235B-A22B across four hardware/precision configurations, MoE-Prefill delivers 1.35-1.37x throughput over the strongest distributed baseline on real-world workloads and up to 1.59x on long-context synthetic workloads, sustaining 29.8-36.2% per-GPU model FLOPs utilization.

Zhaoyuan Su, Olatunji Ruwase, Karthik Ganesan +5

University of Virginia · 2Snowflake AI Research · 3Harvard University

Mixture-Of-Expert Inference Prefill Mixture-Of-Experts Localized Lora-Moe Inference Workloads Workload+2

May 1, 2026cs.LG

Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts

Sparse MoE routing fails at domain transitions, where the current token belongs to one distribution and the next to another. In a controlled experiment (4 experts, 5 seeds), standard affinity routing assigns only 0.006 +/- 0.001 probability to the correct expert at the transition. Three lightweight gate modifications raise this to 0.748 +/- 0.002 (124x), cutting experts needed for 99% coverage from infeasible to a small constant: temporal memory (beta), a per-expert LIF membrane potential accumulating routing context across tokens; precision-weighted gating (Pi), a per-expert inverse variance of recent prediction error, yielding 31x contrast between reliable and unreliable experts; and anticipatory routing, a next-state predictor conditioned on the beta-accumulated hidden state. The mechanisms draw from Friston's Free Energy Principle and use LIF dynamics from spiking neural networks. An ablation across all 2^3 subsets reveals a super-additive beta x Ant interaction: anticipation alone gives nothing (+0.000 +/- 0.001); beta alone gives modest gain (+0.295 +/- 0.013); combined they close 75% of the oracle gap (+0.741 +/- 0.002, exceeding the sum by +0.446 +/- 0.014). This is structural: a stateless predictor cannot detect approaching transitions because pre-transition tokens are distributionally identical to within-domain tokens. In a character-level MoE LM (5 seeds), beta-routing reduces transition-step BPC from 6.56 +/- 0.01 (Standard) to 4.01 +/- 0.15 (beta-MoE); the beta + Ant gate places 0.86 +/- 0.02 probability on the correct domain expert before that domain appears in input, vs 0.42 +/- 0.12 for Standard MoE. Reference implementations (~200 lines each): https://github.com/russellwmy/affinity-is-not-enough

Man Yung Wong

Russell · Independent Researcher

Mixture-Of-Experts Localized Lora-Moe Free Energy Principle Lfsr-Based Stochastic Leaky Integrate-And-Fire Neuron

Apr 29, 2026cs.LG

Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning

LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation capacity of Mixture-of-Experts (MoE). However, existing LoRA-MoE frameworks typically adopt a fixed and uniform expert configuration across heterogeneous Transformer modules (\eg, attention query/key projections and MLP gating networks), ignoring their distinct functional roles and capacity requirements. This design leads to localized over-provisioning, redundant trainable parameters, and unnecessary optimizer-state overhead. Moreover, prior methods enforce load balancing among experts throughout training. Although beneficial in the early stage, this constraint becomes restrictive once routing patterns stabilize, limiting expert specialization on downstream tasks. In this paper, we propose DMEP, a novel LoRA-MoE fine-tuning framework based on Dynamic Module-wise Expert Pruning. DMEP tracks expert utilization during training and physically removes low-utility experts on a per-module basis, yielding a more compact expert structure tailored to different modules. The pruned model then continues training without the load-balancing constraint, freeing the remaining experts to focus entirely on the downstream task and develop specialized expertise. By jointly adapting module-wise expert capacity and eliminating unnecessary balancing, DMEP improves both parameter efficiency and training efficiency. Extensive experiments on multiple reasoning benchmarks show that DMEP reduces trainable parameters by 35%--43% and improves training throughput by about 10%, while maintaining or surpassing the downstream reasoning accuracy of uniform LoRA-MoE baselines.

Weihang Li, Jianchun Liu, Hongli Xu

School of Computer Science and Technology, University of Science and Technology of China, China · Suzhou Institute for Advanced Research, University of Science and Technology of China, China

Parameter-Efficient Fine-Tuning Methods Mixture-Of-Experts Localized Lora-Moe Model Fine-Tuning Experts Transformer Architectures

Apr 20, 2026cs.LG

MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression

KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensional KV tensor -- token eviction (sequence), quantization (precision), low-rank projection (head dimension), or cross-layer sharing -- but apply the same recipe to every layer. We show that this homogeneity leaves accuracy on the table: different layers respond very differently to each compression operation, and the optimal per-layer mix of eviction and quantization is far from uniform. We propose MoE-nD, a mixture-of-experts framework that routes each layer to its own (eviction-ratio, K-bits, V-bits) tuple under a global memory budget. An offline-calibrated greedy solver chooses the routing that minimizes predicted quality loss; at inference time, per-layer heterogeneous eviction and quantization are applied jointly through a single attention patch. On a 4-task subset of LongBench-v1 (16k inputs, n=50 per task, adapted reasoning-model protocol; see section Experiments), MoE-nD's hetero variant matches our uncompressed 1.9~~GB baseline at 14x compression (136~~MB) while every other compressed baseline we tested (1d, 2d_uniform, 2d) at comparable or smaller memory stays under 8/100. The gains hold on AIME reasoning benchmarks (+6 to +27 pts over the strongest per-layer-quantization baseline across eight configurations). Two null results -- MATH-500 and LongBench's TREC -- share a principled cause (short inputs, solver picks keep=1.0 on most layers), cleanly characterizing when per-layer eviction routing has headroom to help.

Libo Sun, Peixiong He, Po-Wei Harn +1

Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA · Department of Information Management, National Central University, Taoyuan, Taiwan

Key-Value Cache Compression Eviction LLM Inference Optimization Data Compression Methods Localized Lora-Moe

Apr 1, 2026cs.CL

StanceMoE: Mixture-of-Experts Architecture for Stance Detection

Actor-level stance detection aims to determine an author expressed position toward specific geopolitical actors mentioned or implicated in a text. Although transformer-based models have achieved relatively good performance in stance classification, they typically rely on unified representations that may not sufficiently capture heterogeneous linguistic signals, such as contrastive discourse structures, framing cues, and salient lexical indicators. This motivates the need for adaptive architectures that explicitly model diverse stance-expressive patterns. In this paper, we propose StanceMoE, a context-enhanced Mixture-of-Experts (MoE) architecture built upon a fine-tuned BERT encoder for actor-level stance detection. Our model integrates six expert modules designed to capture complementary linguistic signals, including global semantic orientation, salient lexical cues, clause-level focus, phrase-level patterns, framing indicators, and contrast-driven discourse shifts. A context-aware gating mechanism dynamically weights expert contributions, enabling adaptive routing based on input characteristics. Experiments are conducted on the StanceNakba 2026 Subtask A dataset, comprising 1,401 annotated English texts where the target actor is implicit in the text. StanceMoE achieves a macro-F1 score of 94.26%, outperforming traditional baselines, and alternative BERT-based variants.

Abdullah Al Shafi, Md. Milon Islam, Sk. Imran Hossain +1

Department of Computer Science and Engineering, Khulna University of Engineering & Technology

Cross-Topic Arabic Stance Detection Bert-Based Models Detection Transformer Mixture-Of-Experts Architectures Motion-Language Alignment Mixture-Of-Experts+2

Mar 27, 2026cs.CV

MOOZY: A Patient-First Foundation Model for Computational Pathology

Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain largely slide-centric, often depend on private data and expensive paired-report supervision, and do not explicitly model relationships among multiple slides from the same patient. We present MOOZY, a patient-first pathology foundation model in which the patient case, not the individual slide, is the core unit of representation. MOOZY explicitly models dependencies across all slides from the same patient via a case transformer during pretraining, combining multi-stage self-supervision with scaled low-cost task supervision. In Stage 1, we pretrain a vision-only slide encoder on 77,134 public slide feature grids using masked self-distillation. In Stage 2, we align these representations with clinical semantics using a case transformer and multi-task supervision over 333 tasks from 56 public datasets, including 205 classification and 128 survival tasks across four endpoints. Across sixteen held-out tasks, MOOZY improves macro weighted F1, balanced accuracy, and macro weighted ROC-AUC relative to PRISM by +4.19%, +7.93%, and +6.95%, respectively. MOOZY is also parameter efficient with 85.77M parameters, 14

\times

smaller than GigaPath. These results suggest that patient-level pretraining yields transferable embeddings, providing a path toward scalable patient-first histopathology foundation models.

Yousef Kotp, Vincent Quoc-Huy Trinh, Christopher Pal +1

CSSE, Concordia University, Montréal, Canada · Mila – Québec AI Institute, Montréal, Canada · CHUM, Université de Montréal, Montréal, Canada +4

Pathology Foundation Models Computational Pathology Medical World Model Multiple Instance Learning Wireless Foundation Models Localized Lora-Moe+1