Mixture-of-Experts Models

Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands continuous capability expansion, making Multimodal Continual Instruction Tuning (MCIT) essential. Existing methods either update all tasks with a shared parameter set or allocate dedicated modules for each new task. Shared updates force heterogeneous tasks to compete, causing forgetting of learned capabilities. Conversely, isolated expansion prevents interference but severely limits parameter efficiency over long task streams. To address this dilemma, we propose CRAM. Specifically, by isolating task-specific patterns into independent modules, CRAM mitigates catastrophic forgetting across tasks. To further boost parameter efficiency, we utilize adaptive-rank instantiation to identify the capability gap between existing expert capability and new task demands, and dynamically allocate only the necessary parameters. To ensure stable reuse among tasks, centroid-guided routing recognizes and activates existing experts' capabilities, while an orthogonality penalty confines new updates to task-specific directions, preventing re-learning general capability. Extensive experiments across diverse benchmarks consistently demonstrate its superiority over existing methods.

Model merging offers a training-free way to combine multiple post-trained expert models, but merging experts obtained through reinforcement learning (RL) remains challenging. Existing spectral merging methods often assume that leading singular directions contain the main task signal, while lower-energy residual components can be compressed, selected, or attenuated to reduce interference. We find that this assumption does not hold for RL task vectors: after decomposing each task vector into a leading spectral head and a residual component, both parts can independently recover substantial behavior knowledge, while exhibiting different merging properties. The head is highly concentrated and informative but more prone to sharp cross-expert conflicts, whereas the residual component is more dispersed and provides a more stable basis for aggregation. Based on this observation, we propose ResMerge, a residual-based spectral merging framework for RL experts. ResMerge first constructs a stable residual backbone with Spherical Residual Consensus Adaptation, which estimates a reliability-weighted consensus direction on the Frobenius sphere. It then reintroduces leading-head information through a Lightweight Head Correction module gated by positive cross-expert agreement. Experiments across multiple RL expert groups and capability domains show that ResMerge better preserves expert capabilities than representative task-vector and spectral merging baselines. The implementation of ResMerge is publicly available at https://github.com/sunyd0303-cpu/ResMerge-release.

Traffic sign detection is a fundamental component of environmental perception in autonomous driving and intelligent transportation systems. However, most existing detectors rely on static inference with globally shared parameters, limiting their ability to adapt to diverse and unstructured traffic scenarios. As a result, a single static model often struggles to simultaneously handle both clear near-range samples and challenging conditions such as distant small targets or adverse weather environments. To address this limitation, we propose CBDES MoE TSR, a hierarchically decoupled heterogeneous mixture-of-experts(MoE) framework for traffic sign recognition. The proposed framework departs from the conventional globally shared parameter paradigm by introducing a heterogeneous You Only Look Once (YOLO) expert pool together with a lightweight gating network, enabling an image-level dynamic routing mechanism. Based on the semantic characteristics of the input image, the gating module selectively activates the most suitable expert model from the expert pool, enabling a shift from fixed parameter fitting to on-demand dynamic representation. This design enhances feature extraction capability for specific scenarios while maintaining controlled inference overhead. Experimental results demonstrate that the proposed method achieves a remarkable balance between detection accuracy and efficiency on the composite traffic sign dataset. Specifically, our method attains an mAP50-95 of 76.8%, yielding a 2.3% improvement over the baseline method (74.5%) while simultaneously reducing computational overhead by approximately 39.4%. These findings robustly validate the effectiveness of the proposed approach.

Pre-propagation graph neural networks (PPGNNs) push all graph-dependent computation into a preprocessing step and train only on the resulting dense hop features, which makes them highly scalable. A puzzle in this regime is that more complex hop aggregators do not reliably outperform simpler ones: on many benchmarks, a plain MLP-based aggregator matches or beats hop-attention variants. We revisit this behavior from a graph-filter perspective. Over a precomputed diffusion basis, existing PPGNNs differ mainly in how filter coefficients are shared across nodes and feature channels, rather than simply in raw aggregator capacity. MLP-based architectures learn channel-dependent filters that are largely shared across nodes, while hop-attention-based architectures learn node-dependent mixtures that are largely shared across channels. This reveals a missing regime in standard PPGNN designs: joint node- and channel-adaptive filtering under the pre-propagation computational contract. We propose FilterMoE, a mixture-of-experts PPGNN in which a small bank of learnable Chebyshev filter experts is routed jointly over nodes and channels by a 3D gating tensor. Across eleven homophilic and heterophilic benchmarks, FilterMoE outperforms strong PPGNN baselines on nine datasets and ranks first on all three large-scale benchmarks, improving the average test score by 1.53 points. These results establish joint node-channel filter routing as a robust alternative to dataset-specific hop-aggregator selection.

Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources. However, existing deep reinforcement learning (DRL) schedulers remain limited by rigid, single-path inference architectures that struggle to handle diverse scheduling scenarios. We introduce $\textbf{DEFT}$ ($\textbf{D}$eadline-p$\textbf{E}$rceptive Mixture-o$\textbf{F}$-Exper$\textbf{t}$s), an innovative DRL policy architecture that leverages a specialized mixture of experts, each trained to manage different levels of deadline tightness. To our knowledge, DEFT is the first to introduce and validate a Mixture-of-Experts architecture for dynamic cloud workflow scheduling. By adaptively routing decisions through the most appropriate experts, DEFT is capable of meeting a broad spectrum of deadline requirements that no single expert can achieve. Central to DEFT is a $\textbf{graph-adaptive}$ gating mechanism that encodes workflow DAGs, task states, and VM conditions, using cross-attention to guide expert activation in a fine-grained, deadline-sensitive manner. Experiments on dynamic cloud workflow benchmarks demonstrate that DEFT significantly reduces execution cost and deadline violations, outperforming multiple state-of-the-art DRL baselines.

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.

Robotic manipulation requires the effective integration of heterogeneous inputs, including visual observations, language instructions, and trajectory representations, to generate accurate actions. Existing transformer-based policies typically process these heterogeneous modalities within a shared parameter space, which often leads to modality interference and inefficient representation learning, especially in data-scarce scenarios. While Mixture-of-Experts (MoE) offers a scalable solution through expert specialization, conventional routing mechanisms are often sensitive to such cross-modal representation discrepancies, resulting in unstable expert assignment and expert collapse. In this work, we propose MATE (Multi-ModAl TrajEctory Policies), a novel trajectory prediction framework built upon MoE. Specifically, we introduce a Multi-Modal MoE architecture to achieve fine-grained sub-token feature decoupling, and design a cross-modal cosine router for stable and scale-invariant expert assignment across heterogeneous modalities. We further employ temperature-controlled routing and stochastic noise injection to improve expert balance and prevent premature routing collapse under scarce demonstrations. Experiments on the LIBERO benchmark show that our MATE consistently outperforms prior work under data scarcity. It achieves a 4.75% improvement in average success rate over the trajectory-guided counterpart. Real-world experiments on robotic ping-pong also suggest that the predicted trajectories can provide useful guidance for downstream robotic execution, further indicating the practical feasibility of our algorithm.

Sparsely activated Mixture-of-Experts (MoE) models scale capacity via conditional computation, but distributed inference suffers from cross-GPU expert communication and routing-induced load imbalance. Existing placement methods reduce this cost by co-locating frequently co-activated experts; however, they derive a single deployment plan from globally aggregated routing traces, thereby averaging away the heterogeneous, task-specific co-activation patterns that actually drive communication in multi-task serving. We observe that expert co-activation is strongly task-conditioned: pairs tightly coupled in one task family are often uncorrelated in another, so effective deployment should group experts by task-aware co-activation rather than by a task-agnostic average. Based on this insight, we propose \emph{Task-Aware Coactivation Grouping} (TACG), a deployment-time framework that uses family-specific dispatch and co-activation traces to derive per-expert task-family preferences, reweights the co-activation graph so that intra-family locality dominates grouping, and assigns each expert to a primary GPU under exact capacity constraints. To keep the static placement robust under online workload skew, we further introduce \emph{Generic Expert Shared Replication} (GESR), a lightweight companion that identifies generic experts with consistently central co-activation profiles, replicates them across a small set of secondary GPUs, and applies locality- and load-aware selection at serving time. Experiments on three representative open-source MoE models demonstrate that our framework reduces the average communication cost by 31.39% over the baseline, while preserving an average Jain fairness index of 0.9975. This advantage persists even under severe distribution shifts in the inference data, consistently outperforming strong baselines.

SwiGLU has become a standard gated activation in modern Transformer MLPs, yet its gate sharpness -- the smoothness and selectivity of the gating function -- is typically fixed throughout training. In this work, we propose Confidence-Aware SwiGLU ($κ$-SwiGLU), a variant of SwiGLU for Mixture-of-Experts (MoE) models that adjusts expert gate sharpness according to token-level routing confidence. Specifically, $κ$-SwiGLU parameterizes the SiLU gate sharpness coefficient as a learnable function of the router logit, enabling each expert gate unit to interpolate between smooth, broadly active gating and sharp, selective gating. We evaluate $κ$-SwiGLU on the FineWeb-Edu dataset across MoE Transformer models ranging from 8 to 28 layers. Across these settings, $κ$-SwiGLU improves mean CORE performance while adding negligible parameters and incurring only a small computational overhead, demonstrating that confidence-aware gate sharpness is a promising mechanism for improving MoE MLPs. The code is available at https://github.com/askerlee/kappa-swiglu.

In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency. This performance variability is inherent to modern accelerators: manufacturing variation, power limits, and thermal conditions introduce measurable execution-time differences across nominally identical GPUs. The core challenge is that MoE execution-time imbalance arises from the interaction of workload skew and hardware asymmetry. Token routing produces uneven and layer-varying expert loads, while GPU throughput depends on device-specific operating characteristics and workload intensity. Prior work mitigates routing skew but assumes homogeneous hardware, optimizing token balance rather than execution latency. As a result, even balanced token assignments can leave hardware-induced stragglers unaddressed. Thus, we propose Variability-Informed Binning of Experts (ViBE), a hardware-aware expert placement framework that minimizes execution-time imbalance across GPUs. ViBE combines per-GPU performance modeling with expert activation profiling to assign high-load experts to faster devices and low-load experts to slower ones, reducing layer-level stragglers without modifying model semantics or hardware. Because both workload characteristics and effective GPU throughput can shift across serving conditions, ViBE supports lightweight recalibration under workload/performance drift to refresh its routing and performance estimates when needed. Results show that ViBE consistently reduces execution-time imbalance and improves SLO attainment by 14%, while lowering P90 TTFT by up to 45%. We further show that the impact of hardware variability increases at scale, making variability-aware placement important for efficient, high-utilization LLM serving.

Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to relevant experts, yet introduce a critical vulnerability: Safety Sparsity, where safety capabilities concentrate in few experts, making them susceptible to adversarial bypassing. Meanwhile, conventional alignment methods uniformly adapt all parameters, ignoring their functional differences and inadvertently degrading performances. To address these challenges, we propose MESA (MoE Safety Alignment), a targeted alignment framework for MoE-based LLMs that strategically decentralizes safety responsibility to maximize coverage while minimizing interference with utility. Based on Optimal Transport (OT) theory, MESA operates through two mechanisms: (1) Expert Capacity Reallocation uses a transport cost matrix to distribute safety duties to the most cost-effective experts, and (2) Dynamic Routing Refinement constrains the router to precisely activate these decentralized modules. Experiments show that MESA achieves robust defensive performance against varied harmful benchmarks while preserving helpfulness. Code is available at https://github.com/lorraine021/MESA.

Mixture-of-Experts (MoE) has become the dominant architecture for frontier language models. To meet this demand, production frameworks have built optimized MoE training stacks over years of engineering effort. Yet evolving these stacks for new architectures and system optimizations remains expensive. With the rise of AI coding agents, they could automate parts of training-framework development and accelerate this evolution. But applying them to these existing frameworks carries hidden costs, invisible to today's throughput-only evaluations. We name this missing dimension agent-task efficiency (ATE): the cost of using coding agents to understand, operate, and extend a framework. Grounded in four agent-native design principles, we build PithTrain, a compact, agent-native MoE training framework. We further introduce ATE-Bench, covering real-world training-framework tasks. Our evaluation shows PithTrain matches the throughput of production frameworks, and on ATE-Bench, PithTrain enables higher agent-task efficiency, with up to 62% fewer Agent Turns and 64% less Active GPU Time.

We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-purpose language model specialized in software engineering, spanning code generation and editing, debugging, multi-step reasoning, tool use and function calling, agentic coding, and conversational programming assistance, and it is the successor to the completion-focused 4B dense Mellum model. The architecture builds on the Mixture-of-Experts (64 experts, 8 active) and combines Grouped-Query Attention with 4 KV heads, Sliding Window Attention on three of every four layers, and a single Multi-Token Prediction head that doubles as both an auxiliary pre-training objective and a built-in draft model for speculative decoding; each choice was validated by ablation with inference efficiency on commodity GPUs as a design constraint. Pre-training spans approximately 10.6 trillion tokens through a three-phase curriculum that progressively shifts the mixture from diverse web data toward curated code and mathematical content, optimized with Muon under FP8 hybrid precision and a Warmup-Hold-Decay schedule with linear decay to zero. The pre-trained base is extended to a 128K context window via a layer-selective YaRN and then post-trained in two stages (supervised fine-tuning followed by RLVR), yielding two released variants: an Instruct model that answers directly and a Thinking model that emits an explicit reasoning trace before its final answer. Across code generation, math and reasoning, tool use, knowledge, and safety benchmarks, Mellum 2 is competitive with open-weight baselines in the 4B-14B range while running at the per-token compute of a 2.5B dense model. We release the base, instruct, and thinking checkpoints, together with this report on the architecture decisions, data pipeline, and training recipe behind them, under the Apache 2.0 license.

Sparse Mixture of Experts (SMoE) architectures improve the training efficiency of Large Language Models (LLMs) by routing input tokens to a selected subset of specialized experts. Despite their remarkable success, both training and inference in SMoE models suffer from the expert collapse issue (Chi et al., 2022), which degrades model performance. Prior studies primarily focus on improving the router; however, such methods rely on training from scratch or fine-tuning, which requires high computational and data-processing costs. Furthermore, we demonstrate that, despite these efforts, the issue persists when advancing well-pretrained SMoE models, as evidenced by both theoretical and empirical results. To fill that gap, we analyze the advanced SMoE models and observe that the eigenvectors of expert weight matrices encode rich semantic information, pointing to an effective alternative to conventional routing strategies. Building on this insight, we propose Singular Value Decomposition SMoE (SSMoE), a novel and training-free framework that leverages spectral properties of the expert weights to address the collapse issue and enhance model performance. Extensive experiments across diverse language and vision tasks, under both clean and corrupt data settings, demonstrate the strong generalization and robustness of SSMoE. Our findings highlight how a deeper understanding of model internals can guide the development of more effective SMoE architectures. Our implementation is publicly available at https://github.com/giangdip2410/SSMoE.

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

Various algorithms have been proposed to address the challenges posed by class-imbalanced learning from real-world data with long-tailed distributions. While these algorithms reduce prediction bias through rebalancing techniques, they often introduce increased prediction variance as a trade-off. Several multi-expert learning algorithms aim to address this variance but involve complex procedures. We propose a new multi-expert learning algorithm, called the dual-axis multi-expert learning (DAMEL), which reduces both bias and variance of predictions by using multiple experts along both representation and time axes. Along the representation axis, DAMEL concatenates the representations of multiple experts and trains an auxiliary balanced classifier simultaneously with the concatenated representations. Along the time axis, DAMEL aggregates network weights across training epochs, employing these aggregated weights during testing. Experimental results demonstrate that DAMEL reduces both bias and variance of predictions, highlighting its effectiveness in class-imbalanced learning.

Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this work, we study multilingual routing dynamics during continual pre-training of an English-centric MoE model on a multilingual corpus, analyzing how expert usage varies across languages. We find that continual multilingual pre-training leads to diffused, language-agnostic routing in early and middle layers, with language specialization primarily emerging in the final layers. We also show that token-level vocabulary overlap between languages plays an important role in how languages are routed. Motivated by these findings, we propose a parameter-efficient adaptation strategy that updates language-specific and shared experts in the final MoE layers. Experiments on MultiBLiMP and Belebele show that our method achieves a strong performance-efficiency trade-off, attaining competitive performance relative to fine-tuning complete final layers, while updating less than 2% of the parameters. Overall, our findings provide insights into where and how language specialization emerges in MoEs during continual pre-training and provide practical insights for low-resource multilingual adaptation. Our code is available at https://github.com/aditi184/moe-routing-adaptation.

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.

We propose a minimal dynamical model of adaptive softmax routing for a two-expert Mixture-of-Experts (MoE) layer. The model is obtained as a mean-field limit of a discrete reinforcement rule: the selected expert receives a small score increment, while all scores undergo regularizing decay. In the symmetric case the limiting system has a supercritical pitchfork bifurcation: for weak feedback there is a unique stable balanced state, whereas above a critical feedback strength two stable asymmetric states appear. When an external asymmetry is added, the pitchfork unfolds into a pair of fold bifurcations forming a cusp in the control-parameter plane. We derive exact parametric equations for the bifurcation set and the local normal form of the cusp catastrophe. Numerical experiments connect this picture to empirical expert load, a small trainable MoE model, hard top-1 PyTorch routing, and a small classification experiment on digits. The results provide a controlled low-dimensional mechanism for abrupt transitions to load imbalance in adaptive MoE routers.

Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Existing fine-tuning approaches treat MoE models as monolithic learners, ignoring the heterogeneous routing structure that develops during pretraining. We validate across multiple MoE models and downstream tasks that middle layers form a language-universal alignment zone where routing divergence strongly predicts per-language task performance gaps. Building on this observation, we propose RA-MoE (Routing-Aligned MoE Fine-Tuning), a three-stage framework that categorizes parallel task examples into a four-way taxonomy (cc/ci/ic/ii) based on correctness in English and the target language, identifies task-relevant experts in the middle layers, and augments standard SFT with a routing alignment loss that encourages target-language routing on ci-type examples to follow the English task-expert activation pattern. Experiments across three MoE models, three tasks, and six target languages demonstrate that RA-MoE consistently outperforms standard SFT and strong baselines including Routing Steering and RISE, with the ci proportion of a task-language pair serving as a reliable predictor of alignment benefit.

Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-prefill aggregation, to prefill-decode (P/D) disaggregation, and most recently to operator-level Attention-FFN Disaggregation (AFD). This trend is especially important for mixture-of-experts (MoE) models, where memory-bound attention, compute-intensive expert FFNs, and MoE dispatch/combine communication create distinct resource demands. AFD further exposes this heterogeneity by placing attention and MoE-FFN execution on separate GPU groups. Each level of disaggregation deepens the scheduling design space across workload characteristics, resource allocation, and interconnect topology, raising the central question: when does each level actually pay off? We systematically characterize this trade-off for MoE inference across realistic workloads spanning input/output sequence lengths, prefix-KV reuse, and per-user latency constraints. Using chunked-prefill and P/D disaggregation as baselines, we study the benefits and limits of AFD at scale through a framework that fuses on-device kernel measurements with high-fidelity network simulation. Under strict TTFT/TPOT SLOs, AFD sustains around 4k tokens/s of system throughput on DeepSeek-V3.2 across chat, coding, and agentic-coding workloads, where non-AFD deployments are infeasible. We distill concrete takeaways for jointly optimizing throughput and interactivity, including how to partition attention and FFN across GPUs as a function of workload and model architecture, providing design principles for current rack- and cluster-scale deployments as well as future disaggregated AI infrastructure.

With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding \emph{\ie} image-to-video transfer learning has become a dominant paradigm. To achieve superior performance, it raises as an effective strategy among recent advances to employ Mixture-of-Experts (MoE) to enhance VLMs' temporal modeling capabilities. However, conventional MoE designs suffer from expert homogenization, where all experts act as identical generalists, inefficiently learning spatio-temporal features from undifferentiated video streams. To overcome this problem, we propose VidPrism, a novel heterogeneous temporal Mixture-of-Experts framework. VidPrism pioneers a division of labor by deploying functionally specialized experts, each assuming a role ranging from spatial understanding to temporal modeling. To feed these specialists appropriately, we introduce a content-aware, multi-rate sampling module that dynamically generates streams ranging from semantically rich to motion-focused representations, providing specialized inputs for experts. Furthermore, a dynamic, bidirectional fusion mechanism enables synergistic information exchange between these pathways, leading to a comprehensive video representation. Extensive experiments on various video recognition benchmarks demonstrate that VidPrism achieves state-of-the-art performance and effectively fosters expert specialization. Our source code is available at \href{https://github.com/Lrrrr549/VidPrism.git}{https://github.com/Lrrrr549/VidPrism.git}.

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.

Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Haskell, OCaml, and Scala chronically underexplored, with even frontier models performing substantially worse on FPLs. Fine-tuning is a natural remedy, but our experiments show that per-language fine-tuning fails to capture shared functional abstractions, while merged multi-language fine-tuning introduces cross-language interference. To address this, we introduce FPMoE, a lightweight, open-source code generation model built on a sparse Mixture-of-Experts (MoE) architecture with three language-specific routed experts (one each for Haskell, OCaml, and Scala) and a shared expert that captures cross-language functional patterns such as monadic reasoning and type-directed programming. This design resolves both failure modes simultaneously: dedicated experts eliminate interference, while the shared expert preserves abstractions that per-language models miss. On FPEval, FPMoE substantially outperforms fine-tuned baselines and, with only 3B active parameters, matches the performance of much larger models including DeepSeek-Coder-6.7B, Qwen2.5-Coder-14B-Instruct, and Qwen3-Coder-30B-A3B.

Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining high model capacity. However, in memory-constrained inference scenarios, only a small set of experts can be cached. Experts not in the cache must be fetched from slow external storage (e.g., UFS), leading to frequent evictions and substantial I/O overhead. We propose ReMoE, a router fine-tuning framework designed to boost token-wise expert reuse. ReMoE biases the router toward recently selected experts, producing temporally stable routing that better matches cache locality constraints. By increasing short-horizon expert reuse, ReMoE reduces expert fetches from storage without adding inference-time computation. Experiments on DeepSeek and Qwen models show that ReMoE improves expert reuse by 26% while maintaining downstream task performance. Real-system evaluations further confirm these benefits, improving output throughput by 8.4% under vLLM GPU-CPU expert offloading and reducing TPOT by 43.6-49.8% under llama.cpp on Jetson Orin NX, corresponding to a 1.77-1.99$\times$ decode speedup across diverse workloads. Checkpoints and usage instructions are available at https://github.com/BUAA-OSCAR/ReMoE.

In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cross-distribution generalization. Our contributions are threefold: (1) We introduce a Residual Refined Expert (R2E) architecture that enhance expert expressiveness via residual refinement; (2) We design an instance-level gating mechanism that learns distribution-aware instance representations and routes inputs to suitable modules; (3) We propose a mixed-distribution training mechanism equipped with Dynamic Weight Adaption (DWA), which dynamically reweights training data from different distributions to emphasize more informative ones. Extensive experiments show that R2E-IG achieves competitive performance against state-of-the-art baselines on both in-distribution and out-of-distribution instances across synthetic and benchmark datasets. Moreover, R2E-IG is generic and can be easily integrated into existing DRL-based methods to further improve performance.

Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing approaches typically integrate these signals at either the input level (e.g., injecting behavioral embeddings into the token space) or the output level (e.g., contrastive alignment of separate encoders), suffering from distribution gaps or lack of end-to-end task supervision. In this work, we introduce L2Rec, which unifies behavioral and semantic understanding at the parameter level of LLMs. Our key insight is that the same set of Transformer parameters can serve as a shared medium for both views: by applying view-specific, personalized low-rank perturbations via a Dual-view Personalized Mixture-of-Experts (DPMoE) mechanism, L2Rec enables a single LLM backbone to produce complementary behavioral and semantic adaptations for each user with minimal representation-level misalignment. An adaptive cross-view fusion module further integrates the dual-view outputs into a unified user preference. Experiments on four datasets show that L2Rec consistently outperforms state-of-the-art baselines, and online A/B testing on a large-scale industrial platform validates significant improvements in key engagement metrics.

The Mixture of Experts MoE architecture is highly promising for resource constrained on device deployments yet training these models from scratch incurs prohibitive costs Current methods attempt to alleviate this by upcycling dense models into MoEs however they often introduce parameter redundancy that degrades inference efficiency Alternatively standard layer pruning mitigates redundancy but inevitably compromises model accuracy To resolve this dilemma we propose Dense2MoE a novel framework that unifies pruning and upcycling through Layer Fusion UpCycling LF UC Guided by hardware Roofline theory Dense2MoE systematically overcomes the inference memory wall by pruning bandwidth heavy attention modules from redundant layers while repurposing their Multi Layer Perceptrons MLPs into MoE experts This structural innovation preserves the models core capabilities and strictly limits active parameters via selective token routing With a modest continual pre training budget Dense2MoE efficiently converts publicly available dense LLMs into on device ready MoE models Extensive experiments demonstrate that Dense2MoE significantly advances the Pareto frontier for on device inference latency versus model accuracy outperforming dense baselines state of the art compression and standard upcycling methods

Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information capacity and density of visual tokens. Addressing this limitation, we propose VEN-VL, a visual ensemble MoE framework for effective and efficient perception following the enrich then compact principle. Specifically, we first enrich the information capacity by unifying the visual representations of different perspectives, and then progressively compact it with adaptive routers in specialized visual experts to enhance the information density. Furthermore, we incorporate the reconstruction ability of vanilla structure via explicit visual supervision, facilitating crucial information preservation. Experimental results demonstrate our superiority in complex visual tasks with few information-condensed tokens, which effectively bridges the gap between performance and efficiency.

While Large Language Models (LLMs) are commonly fine-tuned to handle domain-specific tasks before being applied to vertical applications, adapting them to complex scenarios with diverse specialized knowledge remains challenging. Meanwhile, Mixture-of-Experts (MoE) architecture has risen as a crucial paradigm for training LLMs, and some recent works have also incorporated MoE into Parameter-Efficient Fine-Tuning (PEFT) to propose the Mixture of Low-rank Experts (MoE-LoRA), to enhance the power of low-rank adapters for learning complicated knowledge. However, conventional gating mechanisms in MoE typically apply only a scalar reweighing to selected experts, thereby limiting their underlying capacity of representation and generalization. Motivated and enabled by the low-rank structures in MoE-LoRA, we propose RotMoLE, a specialized MoE framework for low-rank experts featuring an additional rotation gate. Beyond simple scaling, RotMoLE implements a rotation mechanism for each selected expert, enabling superior expert exploitation and specialization for learning diverse data, especially when expert candidates are limited. Empirical results on complex multi-task and multilingual training scenarios validate our effectiveness.

Breast ultrasound imaging is an important noninvasive method for early breast cancer diagnosis, but automatic benign/malignant classification remains challenging due to tumor heterogeneity, blurred boundaries, and data imbalance. To improve feature representation and classification accuracy, this paper proposes the Cross-Stage Attention Mixture-of-Experts Network (CSA-MoE-Net). It adopts a Cross-Stage Attention-enhanced ResNet-18 as the backbone, in which the Cross-Stage Attention module adaptively recalibrates multi-level features, thereby enhancing key tumor features and suppressing redundancy. A three-branch Mixture of Experts (MoE) Block learns complementary features from the Whole Tumor Image, Tumor Core, and Boundary, and an Adaptive Gating Network fuses them to capture morphological, textural, and contextual information. The fused features are denoted as Fused Expert Feature (FEF) in the architecture. Experiments on a balanced dataset of 2,129 breast ultrasound images show that, averaged over 20 independent runs, the model achieves an accuracy of 96.33%, precision of 94.09%, recall of 98.53%, F1-score of 96.25%, and AUC of 99.50%. Compared to the baseline ResNet-18, these metrics improve by 3.01, 0.70, 5.37, 2.98, and 5.42 percentage points, respectively. The proposed mechanism requires no invasive modification and can be seamlessly embedded into VGG-16, DenseNet-121, etc., yielding stable performance gains, thus providing reliable support for computer-aided diagnosis.

Time series forecasting models are increasingly scaled through large Transformer backbones, yet most existing approaches process all series through a shared dense computation path despite substantial heterogeneity in temporal structure. Mixture-of-Experts (MoE) offers a natural alternative by enabling conditional computation, but standard MoE routing leaves expert specialization weakly identified and often unstable during downstream adaptation. We propose AME-TS, a structure-guided sparse time series foundation model that aligns expert routing with interpretable temporal structure. AME-TS first uses a lightweight regime predictor to estimate series-level descriptors, including forecastability, seasonality, trend, and sparsity, and maps them to a soft structural prior over experts. This series-level prior guides token-level routing during training, encouraging structure-aligned specialization. On the GIFT-Eval benchmark, AME-TS delivers a strong accuracy-efficiency tradeoff across model scales: it substantially outperforms existing time series foundation models at small model scales and remains competitive with the strongest models at larger scales, while activating substantially fewer parameters through sparse routing. We further show that AME-TS learns more interpretable routing geometry and substantially more stable expert specialization than standard MoE during fine-tuning on the M5 dataset. These results suggest that structure-aware routing is an effective and reliable way to realize the benefits of sparse expert models for time series forecasting.

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.

Healthcare models are transitioning from unimodal prediction toward multimodal reasoning over heterogeneous diagnostic inputs. In computational pathology, for complex tumor subtypes where morphology alone can be challenging to distinguish, pathology reports and molecular measurements may provide additional diagnostic evidence alongside whole-slide images, yet existing models often fail to clarify how diverse signals assemble into recognizable diagnostic concepts. We propose ConceptM$^3$oE (Concept Multimodal MoE), which embeds concept formation directly within interaction-aware mixture-of-experts (MoE) pathways. The architecture decomposes evidence into modality-specific, redundant, and synergistic experts, which are then projected into structured concept bottlenecks mapping latent features to a hierarchy of morphology and biomarker concepts. To prevent the information loss typical of interpretable bottlenecks, we utilize residual pathways within each expert to allow task-relevant signals to flow both through the concepts and directly to the final task prediction, so that high performance is maintained alongside interpretability. Across an institutional pediatric brain tumor cohort and a public glioma cohort, the framework delivers competitive performance to unconstrained models while producing reasoning traces validated by an independent neuropathologist. In data-limited regimes, ConceptM$^3$oE improves limited-data performance, increasing macro-F1 from 56.41% to 66.70% at small training sizes compared to non-concept-informed baselines, while also showing faster training convergence consistent with the regularizing effect of concept learning. This work offers a scalable path toward high-performance medical AI that is inherently verifiable and better aligned with the complex decision-making of clinical practice.

Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of model computation. This paper studies routing behavior of Mixtral 8x7B-Instruct under benign and harmful prompts using two complementary signals: activation-based routing scores derived from expert selection frequencies and gradient-based scores derived from router-gate sensitivities. We analyze expert- and layer-level routing behavior and conduct expert-suppression interventions. The results show that activation-based expert usage is broad and long-tailed, whereas gradient-based importance is concentrated. At expert level, benign and harmful prompt groups remain close under both signals with modest separation. At layer level, activation-based routing is most selective around layers 8-15, while gradient-based importance is concentrated in final layers. Expert classification shows most experts are shared across benign and harmful prompts, though a limited subset shows clear group preference. Top-ranked expert sets show stronger benign-malicious overlap under gradient scores than activation scores, suggesting concentration on a common late-layer expert set. In intervention experiments, suppressing top five benign-dominant experts from activation scores reduces restricted responses from 24 to 14 over 100 prompts, while suppressing gradient-derived experts reduces them from 34 to 22 with fewer unintended reversals. Overall, safety-relevant routing in Mixtral is subtle, depth-dependent, and distributed rather than dominated by a fixed set of experts.

We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer blocks. Existing tools such as $μ$P (requires fixed architectue) or SDE (requires fixed per-step token count) cannot directly solve the hyperparameter transfer problem in MoE setups because Dense to MoE transfer or MoE total experts scaling changes both architecture and tokens per expert. Complete-muE solves this challenge with a two-bridge system: BridgeI maps between dense FFN and Dense MoE by active-width $μ$P with a normalized router scale. BridgeII maps between Dense MoE and sparse MoE by activated-expert scaling, where the first-order SDE LR/WD correction cancels while a bounded residual $σ_0$ shift remains. The resulting transfer rule, which we term as Complete muE, covers changes in activated experts, total capacity, granularity, and shared/group-balanced hybrids for MoE models as well as network width/depth, batch size, and duration changes for general Transformer models. Extensive language model and diffusion model pretraining experiments confirm that complete-muE yields relatively stable hyperparameter optima across model architectures and parameter counts -- with only minor drift consistent with the non-strict SDE behavior of Bridge~II. In practice this drift is small enough that hyperparameters tuned on a single dense reference transfer near-optimally to all MoE configurations -- \emph{tune dense once, transfer to all} is the practical recipe at the core of Complete-muE. This enables MoE models to achieve accelerated convergence speedup over dense models when scaling model capacity without costly hyperparameter search.

Diffusion-based policies have established a new standard for precise robotic manipulation but face a critical scalability bottleneck: high-performance models are computationally expensive, while lightweight alternatives often fail to generalize across diverse multi-task environments. Mixture-of-Experts (MoE) architectures offer a promising path to efficiency by activating only a subset of parameters. However, existing MoE routing mechanisms typically rely on low-level noise or latent statistics, ignoring the compositional nature of manipulation tasks. This can fragment reusable behaviors across experts, limiting interpretability and transferability. We introduce Semantically Structured Mixture-of-Experts Diffusion Policy (SMoDP) for compositional robotic manipulation, a framework that grounds expert specialization in semantic task structure. SMoDP leverages a lightweight, inference-time skill predictor, supervised by offline annotations from Vision-Language Models (VLMs), to route action chunks to experts specialized for specific behavioral phases. To ensure robust assignment, we propose a dual contrastive alignment strategy that grounds multi-modal observations in language-defined skill semantics (Inter-modal) while enforcing routing consistency across visually distinct but functionally related behaviors (Intra-modal). Our approach outperforms representative diffusion and MoE-based baselines on multi-task benchmarks with significantly improved parameter efficiency and demonstrates effective compositional transfer to novel tasks through parameter-efficient fine-tuning. Project website: https://deng-cy20.github.io/SMoDP/

Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these issues but typically ignore the non-uniform impact of label noise across classes, resulting in ineffective correction for tail classes and over-regularization for head classes. To address this issue, we propose Class-Adaptive Rectification with Experts (CARE), a parameter-efficient framework that leverages three complementary supervision sources from vision-language models (VLM): observed noisy labels, VLM text embeddings, and visual features. CARE introduces a class-adaptive expert consensus mechanism that enforces stricter agreement for tail classes and more permissive agreement for head classes based on class frequency. By aggregating high-confidence predictions across these sources, CARE filters unreliable signals and recalibrates class distributions, yielding more reliable rectification under long-tailed distributions. Extensive experiments on both synthetic and real-world benchmarks demonstrate that CARE consistently outperforms state-of-the-art methods, achieving up to 3.0% performance gains. The source code is available at https://github.com/qwq123-study/CARE.

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic review on the MoE metho addressing multimodal challenges remains lacking. Existing surveys tend to evaluate either multimodal learning or MoE independently from method taxonomy, overlooking the unique interplay between them. This survey fills that gap by answering a central question: \textit{How does MoE effectively resolve multimodal challenges?} We approach this from three key perspectives: (1) \textbf{MoE as an Efficient Multimodal Engine:} enabling scalable multimodal modeling by decoupling computational cost from parameter growth and mitigating modality redundancy through selective expert activation; (2) \textbf{MoE as a Multimodal Representation Learner:} integrating complementary multi-opinion expert knowledge to enrich alignment and interaction representations; and (3) \textbf{MoE as a Multimodal Adapter:} providing a modular and flexible mechanism to model imperfect data scenarios such as modality imbalance and missing modality. Through our extensive literature review, we identify critical research gaps, including interpretable routing, expert communication, modality integration, and lifelong multimodal learning. We position this survey as a foundation for future research toward interpretable and sustainable multimodal Mixture-of-Experts system.

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.

Contemporary glioma diagnosis integrates molecular features with histopathology to guide clinical decision-making. However, in clinical settings, divergent imaging protocols result in incomplete MRI sequences, leading to two primary challenges: forcing existing frameworks to discard a large portion of clinical data during training and consequently limiting their clinical applicability. To address these limitations, we propose GMENet, a Generative Mixture of Experts Network for multi-center glioma diagnosis with incomplete imaging sequences. Firstly, we design a Cross-attention-based Gated Generation Module that synthesizes missing sequence features from available sequences via cross-attention and dynamic gating mechanisms, incorporating a cycle-consistency loss to preserve semantic integrity. Secondly, we introduce a Dynamically Weighted Experts Fusion Module that performs mixture-of-experts interaction and confidence-aware fusion over original and synthesized dual-sequence features for multi-task prediction. We evaluate GMENet on a multi-center cohort of 1,241 subjects from four in-house datasets and two public repositories. Experiments show that GMENet expands clinically usable training data by 97%, relative to complete-sequence-only data. Furthermore, it consistently outperforms state-of-the-art methods trained on complete data, demonstrating improved robustness under cross-center distribution shifts.

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths based on their importance, approaching the accuracy-memory Pareto frontier and enabling extreme low-bit quantization. However, existing methods rely on layer-wise importance estimation and overlook router shifts induced by quantization, resulting in suboptimal allocation and routing. In this work, we propose Global Expert-level Mixed-precision Quantization (GEMQ) to overcome these limitations via (1) a global linear-programming formulation that captures model-wide expert importance based on quantization error analysis, and (2) efficient router fine-tuning to adapt routing to quantized experts. These components are integrated into a progressive quantization framework that iteratively refines importance estimation and allocation. Experiments demonstrate that GEMQ significantly reduces memory and accelerates inference with minimal accuracy degradation. Source code is available at https://github.com/jndeng/GEMQ .

Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible. This coarse granularity forces operators to inspect many routine lines per alert. Message-level detection offers finer granularity, but remains challenging. A single event template may correspond to both normal and anomalous messages, failures arise from heterogeneous subsystems, and line-level labeling at scale is impractical. Although large language models (LLMs) can reason over log semantics, applying them to every line is too costly for continuous monitoring. We present FAME (Failure-Aware Mixture-of-Experts), a label-efficient message-level mixture-of-experts framework that uses an LLM only once offline. We annotate at most K labeled lines per template to derive binary normal/anomaly indicators and representative examples. The LLM proposes a partition of templates into failure domains, and a certification step validates the proposal before training. FAME trains a lightweight router and domain experts that run on-premise and output anomaly predictions and failure-domain labels. On BGL, FAME achieves F1 = 98.16 at K = 100 reducing annotation effort by 76x and detects 86.3% of anomalies from unseen EventIDs. On Thunderbird, FAME reaches F1 = 99.95 with perfect recall.

Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting previously acquired abilities. Existing approaches either internalize knowledge by updating model parameters, which induces catastrophic forgetting, or rely on external memory, which fails to genuinely enhance the model's intrinsic capabilities. We propose MoLEM, a generative mixture of latent memory framework based on a dynamic mixture-of-experts (MoE). We treat multiple experts as independent carriers to generate memory. A router selects and weights experts through key-query matching, and the aggregated latent memory is injected into the reasoning process. The base model for reasoning remains entirely frozen, with all experiential knowledge internalized into the additional modules, avoiding catastrophic forgetting. For continual learning, each training stage is paired with a lightweight autoencoder that selects the appropriate routing group at inference, and inputs that match no stage fall back to the pretrained model. Experiments train the framework on continual-learning sequences spanning math, science, and code domains. After training, we evaluate the framework on the corresponding test sets to measure task learning and competence preservation across continual adaptation stages. After the full continual-learning sequence, our method improves the average accuracy by 10.40% over the Vanilla pretrained baseline, while none of the competing methods consistently exceed this baseline across different training orders.

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and parallelism, they largely treat GPU power as a static constraint rather than a controllable resource. In this paper, we present a power-aware runtime for LLM serving, PALS, that treats GPU power caps as a first-class control knob and jointly optimizes them with software parameters such as batch size. The system combines lightweight offline power-performance models with a feedback-driven controller to select configurations that satisfy throughput targets while maximizing energy efficiency. We implement PALS within an existing LLM serving framework, vLLM, demonstrating that it requires no model retraining or API changes. Across multi-GPU systems and both dense and mixture-of-experts (MoE) models, PALS improves energy efficiency by up to 26.3%, reduces QoS violations by 4x to 7x under power constraints, and tracks dynamic power budgets. These results highlight the potential of integrating power control directly into LLM inference runtimes, enabling energy-proportional and grid-interactive AI systems.

Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving distributed learning. However, existing FL methods face a fundamental challenge. Traditional averaging-based approaches suffer from parameter divergence under non-IID conditions, while personalized FL methods overfit to local data and fail to generalize to new clients (cold-start problem). Mixture-of-Experts naturally addresses this by routing heterogeneous data to specialized experts rather than forcing uniform aggregation. In this paper, we propose FedCoE, a Federated Coordinated dual-level mixture-of-Experts framework that effectively balances global generalization with local personalization. FedCoE maintains multiple independent global expert models on the server and employs a shared gating network to dynamically model client-expert correlations during aggregation, effectively mitigating expert drift and gating inconsistency. To address the cold-start challenge, we introduce an adaptive mechanism that enables new clients to immediately leverage the global expert pool without extensive local training. Extensive experiments demonstrate that FedCoE achieves 78.00% global accuracy and 89.32% personalized accuracy on average, outperforming the baseline by 8.82% and 29.19%, respectively. In cold-start scenarios, FedCoE delivers 77.27% accuracy without any local fine-tuning, outperforming baselines by over 12.54%.

AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations: predictive sample placement, adaptive expert relayout, hierarchical collectives, and EP-aware topology. All four rest on two assumptions about the workload. The first is that routing imbalance is correctable by the system layer. The second is that the mock-token benchmarks evaluating them faithfully represent production routing. We introduce DODOCO to test both assumptions. We instrument five MoE checkpoints spanning five sequence-mixer designs (DeepSeek-V2-Lite MLA, DeepSeek-MoE-16B MHA, Qwen3-30B GQA, Nemotron-30B Mamba-2, Qwen3.5-35B GDN) under a 5 by 6 grid of data conditions plus a matched EP scan from 4 to 32 ranks on H100s; both assumptions fail. Scaling EP changes the per-expert max/mean token ratio by at most 5% within every architecture's measurable range: the straggler is intrinsic to the routing decision the model makes, not to how its experts land on ranks. Mock tokens overestimate routing Gini by up to a factor of 2.35 and fabricate a batch-size scaling trend that vanishes the moment real text replaces random IDs. A third pattern, unexpected, emerges from the same matrix: the five architectures cleave into two stable bands. MHA and Mamba-2 (data-resilient) drop to Gini 0.105 and 0.150 on wikitext. MLA and GDN (persistently concentrated) stay above 0.24 on every real-text condition and reach 0.29 to 0.38 on mock. GQA is the intermediate case. These bands, not the EP degree or the mock-data profile, are the right workload input to AlltoAll-aware interconnect and dispatch design.

Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opinion words. Existing models typically learn from the final polarity label, which provides limited guidance for reasoning about sentiment from the context. Motivated by cognitive appraisal theory, we propose an appraisal-aware multi-task learning (MTL) framework for implicit sentiment analysis that provides polarity prediction with two complementary auxiliary tasks: implicit sentiment detection and cognitive rationale generation. However, training several objectives with different targets and sharing a single backbone across tasks in MTL limits flexibility and can lead to task interference. To reduce interference among these related but distinct objectives, we adopt task-level mixture-of-experts models in which all tasks share a common set of experts, and task identity controls the sparse combination of these experts. Our method builds on an encoder-decoder architecture and replaces a subset of encoder and decoder blocks with these sparse mixtures. We use a task-conditioned router to select sparse expert mixtures for each task, and a task-separated routing objective to encourage different tasks to learn distinct expert-selection patterns. Experimental results show that our model outperforms recently proposed approaches, with strong gains on the implicit sentiment subset. Our code is available at https://github.com/yaping166/TRMoE-ISA.

Multimodal survival prediction, a crucial yet challenging task, demands the integration of multimodal medical data (\eg Whole Slide Images (WSIs) and Genomic Profiles) to achieve accurate prognostic modeling. Given the inherent heterogeneity across modalities, the feature decoupling-fusion paradigm has emerged as a dominant approach. However, these methods have the following shortcomings: (1) fail to reduce the redundant information of modality features before decoupling, which negatively affects the feature decoupling and fusion effect;(2) lack the ability to model the fine-grained relationships of the features and capture the local information interactions between intra- and inter-modality features. To address these issues, we propose a \underline{H}ierarchical \underline{D}ecoupling-Fusion \underline{M}ixture-\underline{o}f-\underline{E}xperts (HDMoE) framework with two levels of MoE and \underline{R}andom \underline{F}eature \underline{R}eorganization (RFR) modules.In the first-level MoE, shared experts and routed experts are employed to remove redundant information and extract fine-grained specific features within each modality, while the second-level MoE facilitates fine-grained inter-modality feature decoupling. Besides, we design two RFR modules following each level of MoE to finely fuse intra- and inter-modality features, which can help the model capture more fine-grained relationships between modalities. Extensive experimental results on our private Liver Cancer (LC) and three TCGA public datasets confirm the effectiveness of our proposed method. Codes are available at https://github.com/ZJUMAI/HDMoE.

Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (MoE) architectures offer a promising paradigm for decoupling complex drift patterns, existing approaches are limited by fixed expert pools and memoryless routing, hampering their ability to adapt to abrupt regime shifts. To address this, we propose Dynamic TMoE, a framework that unifies architectural evolution with temporal continuity during learning phase. By detecting distribution shifts via Maximum Mean Discrepancy (MMD), we dynamically instantiate heterogeneous experts and prune redundant ones to optimize capacity. Additionally, a temporal memory router leverages recurrent states and an anomaly repository to ensure stable, context-aware expert selection without requiring test-time updates. Experiments on nine benchmarks demonstrate state-of-the-art performance, reducing MSE by 10.4% and MAE by 7.8%. Code is available at https://github.com/andone-07/Dynamic-TMoE.

Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and spatial misalignment between heterogeneous sensors. Existing bimodal detectors often align or fuse features without assessing the reliability of local cross-sensor correspondence, allowing mismatch artifacts to propagate into the detection head. To address this issue, we propose LER-YOLO, a reliability-aware sparse mixture-of-experts framework for misaligned RGB-infrared UAV detection. LER-YOLO first introduces an Uncertainty-Aware Target Alignment module that resamples visible features toward the infrared reference and estimates a spatial reliability map. This reliability prior is then used by a Reliability-Guided Sparse MoE Fusion module to adaptively select k experts from RGB-dominant, infrared-dominant, and interactive fusion experts, enabling trustworthy cross-modal interaction while suppressing unreliable fusion. Experiments on the public MBU benchmark under a YOLOv5s-family protocol show that LER-YOLO achieves 89.7+/-0.2% AP50 over three independent seeds, with a best result of 89.9%. Extensive ablations, parameter-matched comparisons, synthetic-shift evaluations, and complexity analysis demonstrate that the gains mainly come from reliability-guided expert routing rather than increased model capacity.

Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes. We train sparsely-gated convolutional MoE models with a contrastive objective on natural images and characterise expert specialisation using tools from visual neuroscience. Extending from gating-level to expert-level analyses, we measure per-expert category separability, and per-expert tuning using the most exciting inputs. Extending from category-level to feature-level explanations, we interpret tuning via semantic dimensions derived from a dataset of human behavioural judgements (THINGS). Finally, we use tuning and representational similarity analysis to assess the stability of expertise-allocation across independent initialisations. We find that an animate-inanimate distinction dominates expert partitioning, apparent from gating through to expert readout, and is stable across independently trained models. Although routing statistics suggest relatively sparse, categorical preferences, expert analyses reveal broader tuning to continuous visual and semantic dimensions that extend beyond category boundaries. Experts exhibit similar category-separability to one another, despite distinct feature tuning, demonstrating the explanatory benefits of moving beyond category-level analyses. Together, these results show that expert specialisation in vision MoEs extends well beyond category routing and is better understood by probing fine-grained expert-level tuning and representational structure.

Mixture-of-Expert (MoE) models enable efficient inference by employing smaller experts and activating only a subset of them per token. MoE serving engines distribute experts across multiple GPUs and route tokens to appropriate GPUs at inference time based on experts activated. They process tokens in lock-step fashion, where tokens within a batch must finish processing before proceeding to the next layer. This synchronization barrier acts as a critical bottleneck because the performance of MoE models is limited by the straggler GPU that finishes last. Stragglers emerge when too many heavily used experts are placed on the same GPU or the slowest GPU. While prior works place experts that balance token loads across GPUs, they all overlook GPU variability and often place highly used experts on the slowest GPUs. We propose GEM, GPU-variability-aware Expert Mapping, a framework for GPU variability-aware expert to GPU mapping for MoE models. GEM exploits two insights. First, we must place experts such that each GPU receives non-uniform token loads based on their variability and they all finish processing a layer at about the same time. Our studies show that there are two types of experts: consistent that are used most of the time and temporal that are often used together for the remaining time. Our second insight is that we must place simultaneously used consistent and temporal experts on different GPUs and avoid placing them on slower GPUs to reduce slowdown. GEM gathers the variability profile of GPUs for each model and task and uses the token load distributions per task to map experts to GPUs. Our experiments show that GEM improves end-to-end latency by 7.9% on average and by up to 16.5% compared to the baseline.

The inspection of electrical power line insulators is essential for ensuring grid reliability and preventing failures caused by damaged or degraded insulation components. In recent years, Unmanned Aerial Vehicles (UAVs) combined with deep learning-based vision systems have emerged as an effective solution for automating this process. However, insulator fault detection remains challenging due to small defect regions, heterogeneous fault patterns, complex backgrounds, and varying imaging conditions. To address these challenges, this paper proposes an optimized YOLO26-MoE, a novel object detection architecture that integrates a sparse Mixture-of-Experts (MoE) module into the high-resolution branch of the YOLO26 detector. The proposed modification enables adaptive feature refinement for subtle and diverse fault patterns while preserving the efficiency of a one-stage detection framework. Hyperparameter optimization, final training, and evaluation were coordinated through a tool-augmented Large Language Model (LLM) agent. The proposed model achieved 0.9900 mAP@0.5 and 0.9515 mAP@0.5:0.95, outperforming the latest YOLO versions. These results demonstrate that the proposed model provides an effective and reliable solution for UAV-based insulator fault detection.

Visual image reconstruction from functional Magnetic Resonance Imaging (fMRI) is a fundamental task in brain decoding, providing a crucial pathway for understanding human perceptual mechanisms and developing advanced brain-computer interfaces (BCIs). However, most current methods simply flatten fMRI signals from localized visual cortices into one-dimensional (1D) vectors, mapping them directly into latent spaces such as that of Contrastive Language-Image Pre-training (CLIP). This paradigm not only disrupts the inherent network topology of the brain-leading to limited neuroscientific interpretability-but also overlooks the synergistic contributions of other distributed functional networks in processing high-level visual semantics. To address these limitations, we propose FPED, a Functional-Network Prior-Guided Mixture of Experts (MoE) framework for interpretable brain decoding. FPED explicitly models different functional brain networks as specialized experts and employs adaptive routing to capture their complementary contributions to visual semantic understanding. Unlike conventional homogeneous decoding paradigms, our framework incorporates neurobiologically grounded priors to enable structured and interpretable network-level representation learning. Experimental results demonstrate that FPED achieves highly competitive semantic reconstruction performance with only 0.68B parameters. The learned routing dynamics reveal biologically meaningful correspondence between functional brain networks and modality-specific semantic processing, providing transparent neuroscientific interpretability. This suggests that brain network-aware expert modeling is a promising direction for bridging neural decoding and biologically inspired artificial intelligence.

Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner. Existing dynamic MoE methods usually rely on pre-training from scratch or task-specific adaptation, leaving the practical conversion of fully trained MoE underexplored. Enabling such adaptation would directly alleviate the inference costs by allowing easy tokens to bypass unnecessary expert during serving. This paper introduces Zero-Expert Self-Distillation Adaptation (ZEDA), a low-cost framework that transforms post-trained static MoE models into efficient dynamic ones. To stabilize this architectural conversion, ZEDA injects parameter-free zero-output experts into each MoE layer and adapts the augmented model through two-stage self-distillation, utilizing the original MoE as a frozen teacher and applying a group-level balancing loss. On Qwen3-30B-A3B and GLM-4.7-Flash across 11 benchmarks spanning math, code, and instruction following, ZEDA eliminates over 50% of expert FLOPs at marginal accuracy loss. It outperforms the strongest dynamic MoE baseline by 6.1 and 4.0 points on the two models, and delivers ~1.20$\times$ end-to-end inference speedup.

Expert specialization in Mixture-of-Experts (MoE) models remains poorly understood, with traditional evaluations conflating architectural load-balancing with functional specialization. We introduce DBES, a comprehensive diagnostic framework combining a multi-domain benchmark with five theoretically grounded metrics: Routing Specialization, Normalized Effective Rank, Domain Isolation, Routing Stiffness Score, and N-gram Expertise measures. Critical findings demonstrate distinct specialization paradigms across models: Qwen-series exhibit modular specialization with high domain isolation, while DeepSeek and GLM employ distributed collaboration. However, we emphasize that specialization is a diagnostic dimension, necessary but not sufficient for downstream performance. Most crucially, interventional evidence validates the actionability of these metrics: by using DBES to identify high-specialization expert paths during domain-specific post-training, we achieved 66% to 94.48% improvement in specialized domains with only 15% of original training resources, demonstrating that these diagnostic tools can be converted into concrete optimization operators. This work provides the first systematic methodology for evaluating expert specialization independently of accuracy metrics, offering crucial insights for the design and post-training optimization of next-generation MoE systems.

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a multilingual CPT-enhanced model with its instruct counterpart, they are plagued by a critical trade-off: mitigating parameter conflicts to preserve original abilities inevitably dilutes new language acquisition, and vice-versa. To resolve this conflict, we introduce \method, which upcycles a dense model into a Mixture-of-Experts~(MoE) architecture, allocating different experts to different languages. Alignment ability is then transferred by grafting a MoE-expanded parameter delta~($Δ_{\text{post}}$) to the CPT-enhanced base model, bypassing the complex alignment phase. Experiments demonstrate \method's superiority even against baselines with similar FLOPs or number of parameters; it improves performance on expanded languages while effectively preserving original capabilities. We further show our approach is highly applicable across different models and Post-training deltas.

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.

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.