Mixture-of-Experts Models

Multivariate ocean forecasting must exploit shared evolution in a coupled ocean system while adapting to the heterogeneous statistical and dynamical characteristics of different prediction variables and locations. Fully shared models may lack the flexibility to handle this heterogeneity, whereas fully independent models discard the common ocean context shared across variables. The key question is how to retain shared context in a unified model while allowing computation to specialize according to the prediction target and local state. We propose OceanMoE, a structured conditional sparse Mixture-of-Experts framework that combines sharing and specialization for multivariate ocean forecasting. OceanMoE fuses cross-variable information to construct target-specific local representations and uses them to perform content-conditioned sparse routing at each spatial location, with the number of active experts adapted to router confidence. In the decoder, routing is augmented with a learned geographic bias parameterized by spherical-harmonic spatial bases, while shared residual and seasonal pathways provide common cross-variable and month-dependent context. Experiments on long-horizon autoregressive ORAS5 forecasting show that OceanMoE lowers aggregate forecasting error in both evaluated settings and maintains lower geometric-mean normalized RMSE than the corresponding baselines over most later rollout months. Routing analyses further show that expert allocation varies with prediction targets and spatial locations. These results support structured conditional computation as a modeling strategy for balancing shared ocean context with adaptive specialization.

Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for reducing this parameter count, yet existing methods make pruning decisions for each expert independently, and assume experts' contributions are purely additive. In reality, expert usage in MoEs is inherently cooperative. We derive HOPE (Higher-Order Pruning of Experts), a second-order pruning objective which provably minimizes an upper bound on the error resulting from pruning. We show that REAP (a state-of-the-art first-order pruning method) is a special case of HOPE where interaction terms are ignored. Across three frontier MoE models (up to 122B parameters), two distinct calibration sets, and multiple benchmarks (including math, instruction following, coding, and an agentic suite), we demonstrate that HOPE produces better pruning decisions than existing methods, and its advantage is most pronounced at high pruning rates and on challenging agentic workloads. At 50% pruning, HOPE outperforms all baselines and achieves an average rank of 1.58 out of 5 methods (versus 2.42 for the next-best method, REAP), with gains of up to +6.1% on agentic coding. Over all conditions, HOPE again achieves the best average rank and surpasses every other method in the majority of head-to-head comparisons. By preserving cooperative expert structure that first-order methods ignore, HOPE enables aggressive compression with minimal degradation, particularly on complex tasks where diverse expert combinations are invoked over long sequences.

Scaling laws hold that language models grow more capable with more parameters and more training data. Mixture-of-Experts (MoE) architectures are a remarkable demonstration of these laws, activating only a fraction of an enormous parameter bank for each token. But this success is built on static pretraining data --- the facts and corrections supplied by users during live interactions are a significant untapped source of potential improvement for a deployed model, but cannot be exploited by conventional architectures whose weights are frozen after training. Instead, this newfound knowledge must be placed in the context (by instruction or retrieval) and re-read on every request, only to be discarded afterwards. We seek instead to learn from live interactions by dynamically updating model weights. Inspired by MoEs, we propose the \textbf{Infinite-Parameter LLM}. A compact hypernetwork turns the online data into low-rank modulations of a shared base network, so feed-forward weights are generated from live data, not read from static memory. Whereas existing weight generators are held fixed after reading the context once, we form a Bayesian belief over the generator's latent state and update it online, such that the effective weights are re-derived as our belief evolves during the session. Although the model's memory footprint is constant, the feasible space of generated weights is thus effectively infinite. Representing live data in the weights rather than the prompt amortises compute, frees the context window, persists updates across turns, and can generalise better than in-context use. Our evaluation protocol applies this methodology to in-context learning and retrieval.

AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (MoE) architectures currently fail to satisfy. Expert-based routing improves in-domain learning but may sacrifice cross-modal signals, which appear particularly important for rare (low-prevalence) pathologies in our experiments. To resolve this, we introduce Generalist-Specialist-MoE (GS-MoE), a two-branch (MoE) architecture that couples a cross-modal generalist model with distinct modality-specific specialists (experts) via domain-constrained feature fusion. On RadImageNet (1.35M images, 165 pathologies, three modalities), GS-MoE recovers detection of six low-prevalence pathologies on which every baseline scores F1 $=$ 0, with per-class gains up to +0.60 F1. It attains this while even slightly exceeding dense and specialist-only MoE aggregate baselines (MCC 0.770), while using ${\sim}53\%$ fewer active parameters at inference than the strongest investigated dense model.

Video-based Multimodal sentiment analysis (MSA) must handle information from text, audio, and image sequence in human speaking videos, yet current methods often fail to integrate modalities with task awareness. Most models treat video sentiment prediction as a single task, overlooking its ordinal nature, and their fusion strategies struggle to capture diverse unique and synergic cues across modalities. To address these limitations, we adopt a divide-and-conquer perspective by reformulating MSA as an ordinal regression problem and decoupling it into polarity recognition and intensity prediction. Driven by information theory, we introduce a Mixture-of-Bottleneck (MoB) framework that assigns different latents to polarity- and intensity-specific experts for different modalities. With the learning of information bottleneck, each expert learns compact and task-relevant representations while filtering out redundancy and noise. A multimodal bottleneck routing fusion module then fuses these expert latents with hard mining strategy, guiding the prediction in the ordinal sentiment space. Extensive experiments on 4 MSA datasets and 4 language models show that MoB effectively leverages informative latents from diverse modalities and captures general sentiment structure. Beyond stronger performance, MoB comprehensively captures fine-grained intra- and inter-modal dynamics, enabling more trustworthy localization of nuanced video sentiment signals.

Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the number of experts. Recurrent Transformers achieve parameter efficiency by reusing layer weights, but typically lack the capacity for competitive language modeling. We propose Mixture of Reused Experts (MoRE), a hybrid that shares expert pools across groups of adjacent layers. Each layer retains its own router but selects from a larger shared pool, expanding the diversity of routing combinations without additional parameters. To enable shared experts to distinguish between layers, we introduce lightweight learnable depth embeddings that condition each layer's input before routing. Experiments across three model scales (114M-1.15B parameters) show that MoRE consistently achieves lower perplexity and stronger downstream performance than standard MoEs and state-of-the-art weight-sharing architectures at matched compute and parameter budgets, with only minimal modifications to existing MoE implementations.

In this paper, we present a Mixture-of-Experts (MoE) quantization method based on activation entropy. Although quantization reduces memory and computational costs, it can substantially degrade performance. In particular, performance decline is pronounced in quantized MoE models, where individual experts have a small number of parameters that are sensitive to low-bit representation. Considering that MoE operates as an ensemble model with collaborative contributions from routed experts, a significant performance decline of a particular expert due to quantization can harm model performance. Therefore, we propose Colla-Q, a bit-allocation framework to maintain balanced performance across experts through an activation-entropy-based bit-width allocation algorithm. This approach encourages each expert to operate collaboratively in the quantized model, thereby 1) improving the overall MoE performance and 2) reducing the dependence on the calibration dataset. Since uniformly adjusting each expert's performance facilitates robustness and stability of the MoE model, the proposed MoE quantization method can generalize more consistently across different calibration datasets. Our code is available at: https://github.com/mmai-laboratory/Colla_Q

Mixture-of-experts (MoE) inference on consumer hardware is bounded by weight memory: a 35B-class model is 19.5GB at 4-bit, and sparsity shrinks the compute per token, not the bytes that must be held. Naive offloading to SSD does not help on its own, because layer N+1's experts must be chosen before layer N's output exists, so the reads cannot start early enough to hide behind compute. We present Edge0, a streaming MoE inference engine that closes the gap with a prerouter: a per-layer head predicts the next layer's routing one token ahead, and the prediction is consumed as the routing itself, so the staged expert set equals the routed set and nothing is dropped. An unmerged recovery LoRA, trained on the student path, pays back the quality lost to int4 quantization and routing replacement. On a single 24GB machine, Edge0 serves a 35B MoE at 20tok/s inside 3GiB of peak active memory, within a few points of its fp16 teacher on average across five public benchmarks. An 8B tier runs on the same framework, and the framework, checkpoints, and adapters are open source.

Sparse mixture-of-experts models route each token through a sequence of expert selections. We ask whether the immediately preceding selection adequately summarizes this trajectory for predicting the next router. Using frozen OLMoE and JetMoE models, we measure the held-out predictive gain from earlier expert selections while retaining the most recent selection as a common baseline. In OLMoE, extending the history from one to eleven layers raises router-logit $R^2$ from 0.59879 to 0.66544. A preregistered JetMoE replication yields four-layer gains of 0.14275 and 0.20528 at two target depths, with paired bootstrap intervals above zero. These gains survive nonlinear decoding: adding history to a small multilayer perceptron improves $R^2$ by 0.17137 and 0.21861, whereas nonlinear decoding of the recent state alone adds 0.00139 and 0.00936 over a linear probe. Parameter-matched controls preserve the advantage, and cross-fitted history residuals predict target residuals with $R^2$ of 0.20549 and 0.23556. These findings identify residual predictive structure in expert-selection trajectories beyond adjacent-layer persistence.

The unchecked proliferation of manipulated images on social media platforms has increased the spread of misinformation, posing a severe threat to public trust and information integrity. Modern deepfake detectors typically rely on Vision Transformers (ViTs) to capture the low-level inconsistencies that characterize fully synthetic or locally tampered images. However, the global understanding of such foundation models is not enough to discriminate alone between real and fake multimedia content, especially in challenging scenarios where images are compressed or transmitted through social media. In this paper we pioneer the application of Joint-Embedding Predictive Architecture (JEPA) models to deepfake detection, taking advantage of the generalized representation of visual reality that such World Models have exhibited. We hypothesize, and empirically demonstrate, that the intrinsic world understanding of JEPA models can be used as a strong prior for a deepfake detector. To fully exploit JEPA capabilities, we propose MoE-JEPA, a dual-stream architecture for deepfake detection. By enhancing a V-JEPA 2 backbone with a Residual Mixture-of-Experts (MoE) mechanism, along with a noise stream branch, our model dynamically internalizes forensic knowledge. Furthermore, a Gated Attention Multiple Instance Learning (MIL) module is employed to ensure precise spatial semantic understanding. Evaluated on the SID-Set benchmark, comprising 300K AI-generated, tampered and authentic images, MoE-JEPA establishes a new state-of-the-art with an accuracy of 95.54%, successfully outperforming vastly larger models.

Short-term photovoltaic power forecasting requires models to represent regular solar cycles and weather-driven fluctuations whose importance changes with the forecast horizon. This study develops a hierarchical ensemble that combines temporal neural models, historical analogs, state climatology, and gradient-boosted trees. Solar geometry and numerical weather forecasts describe the expected generation conditions, while horizon-specific convex weights combine complementary predictions. A separate calibration step uses available historical forecast errors to account for recent bias. The framework is evaluated on public PVDAQ data at 15--240-minute horizons and on three GEFCom2014 solar zones at hourly horizons up to four hours. On PVDAQ, the ensemble achieves a daylight capacity-normalized mean absolute error of 4.315%, reducing error by 4.11% relative to full-feature LightGBM and by 6.03% relative to fine-tuned Chronos-2 under identical calibration. Expert-removal experiments identify redundancy within the ensemble. Across three training seeds on GEFCom2014, learned fusion improves upon equal weighting but performs comparably to LightGBM. The results support horizon-specific combination as a useful forecasting strategy while showing that its advantage over strong individual models depends on the dataset and evaluation period.

Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have primarily focused on improving optimization stability and training efficiency, while treating the expert selection as a fixed component. Since routing determines the sparse computation paths that induce output distributions, expert selection offers an additional source of rollout diversity. Through empirical analysis, we find that perturbing expert routing effectively alters model output and increases rollout diversity, which is similar to increasing the decoding temperature. However, direct perturbation can activate unsuitable experts and substantially degrade rollout quality. Motivated by these observations, we introduce Expert-Space Exploration Reinforcement Learning (ESRL), an architecture-aware framework that explicitly explores the expert-routing space of MoE models. ESRL preserves high-confidence experts as anchors, and restricts stochastic routing to a plausible candidate pool, thereby retaining reliable computation paths. The perturbation strength is further adapted according to router entropy to avoid over-perturbation. To mitigate the routing mismatch introduced by perturbation, ESRL records the expert paths used during rollout and replays them during policy optimization. Experiments demonstrate that ESRL achieves the best performance across MoE backbones with top-K, top-1, and shared-expert routing, as well as across mathematics, science, and code tasks without additional sampling or computational cost. Specifically, ESRL on Qwen3-30B-A3B achieves the best among all compared methods, improving average Pass@1 and Pass@8 over GRPO by 3.2 and 4.5 percentage points, respectively. Further analyses of expert utilization and training dynamics provide insights into how exploiting MoE-specific routing structure benefits RL training.

Handwritten text recognition resources are often small and distributed across collections that differ in language, script, document structure, and annotation format, making joint page-level training difficult. We propose ExpertHTR, a unified vision-language framework that addresses this problem through complementary supervision and conditional model capacity. Structural annotations from heterogeneous datasets are first organized through a common Page-Region-Line representation and used to construct four related training tasks for complete transcription, physical-line coverage, text localization, and localized recognition, without requiring additional manual labels. Building on a jointly trained dense model, ExpertHTR introduces a sparse Mixture-of-Experts architecture with an always-active shared branch and conditionally routed full-MLP experts. Sparsegen allows the number of active routed experts to vary with the hidden representation, while routing regularization reduces persistent concentration on a small subset of experts. Experiments on seven heterogeneous handwriting benchmarks show that complementary supervision consistently improves training with page transcription alone, while joint multi-source training provides further gains on most datasets. The proposed sparse expert model further improves the dense baseline on six of the seven sources. The final unified model also substantially outperforms the evaluated general-purpose OCR and vision-language systems on most benchmarks and achieves state-of-the-art performance on the IAM paragraph-level benchmark, while specialized HTR systems remain stronger on several challenging collections.

Mixture-of-Experts (MoE) creates a structural advantage for offloading: only a small fraction of activated experts need to reside in device memory, and if they can be loaded in time for computation, offloading can in principle approach full-load performance, where all model weights reside in device memory. Yet translating MoE's structural advantage into practical offloading gains remains challenging. We propose SeqMoE to bridge this gap. To maximize expert hits, we build predictive memory management: (i) Sequence-to-sequence prediction. We are the first to recast expert activation prediction as sequence modeling, enabling accurate multi-step, multi-layer forecasts that provide a long and reliable window for downstream decisions. (ii) Joint prefetch scheduling. We formulate prefetch scheduling as Job Sequencing with Deadlines to maximize expected expert hits and improve bandwidth efficiency. (iii) Forecast-driven caching. Leveraging the recursive nature of sequence modeling, we introduce a probabilistic Belady policy for future-aware eviction. To eliminate execution bottleneck, we develop (iv) Graph-compatible offloading runtime. We derive general runtime principles encompassing compute-transparent expert placement and synchronization-free orchestration disciplines for end-to-end graph capture. With 45% expert residency, SeqMoE averages a 96.97% hit rate and 80.22% of full-load performance, advancing the state of the art in MoE offloading.

To address the challenges of behavioral multimodality, limited semantic utilization, and long-term error accumulation in vessel trajectory prediction, this paper proposes M3-Former, a multimodal trajectory prediction framework enhanced by large language models (LLMs). The proposed framework incorporates vessel static attributes and navigational intent as semantic priors for long-term trajectory modeling. Specifically, a unified multimodal representation space is constructed, in which static semantic information is encoded by a pre-trained LLM and aligned with dynamic trajectory features through self-attention. To jointly capture global route planning and local motion variations, a dual-granularity Mixture-of-Experts (MoE) architecture is introduced, where sequence-level experts model global navigation trends and token-level experts refine fine-grained maneuvering behaviors. In addition, a Steering-Weighted Cross-Entropy loss is designed to alleviate the long-tail distribution of sparse turning samples and improve prediction accuracy in critical maneuvering scenarios. Experiments on a real-world Danish AIS dataset demonstrate that M\textsuperscript{3}-Former consistently outperforms state-of-the-art baselines across prediction horizons from 1 to 4 hours. In the 4-hour prediction task, the proposed method reduces Average Displacement Error (ADE) and Final Displacement Error (FDE) by 4.4% and 5.1%, respectively, compared with the strongest baseline. Qualitative and ablation analyses further verify that semantic fusion effectively reduces long-term trajectory drift, while the dual-granularity MoE improves robustness in complex waterways and route-branching scenarios. The proposed framework establishes a semantic-guided hierarchical prediction paradigm, in which high-level navigational intent and local motion dynamics are jointly modeled for robust long-term vessel trajectory forecasting.

As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activated Transformers, but the effects of data repetition remains largely unexplored for recently dominant sparse architectures such as Mixture-of-Experts (MoE), despite their increased compute efficiency. We vary data repetition rates across single- and multi-domain data mixes, and across MoE settings, including expert count and granularity. We consistently find, for models ranging from 80M to 1B active (8.5B total) parameters, that MoEs degrade more rapidly under data repetition. This effect increases with sparsity, dictated by total rather than active parameters. While 80M dense models can repeat data over 8x with minimal degradation, MoEs instead begin to suffer at 4x, and deteriorate rapidly, ceding their performance benefits in all-unique data settings to underperform dense models after 32x. We experiment with existing regularization methods as a potential remedy. We find that some methods, such as dropout, can mitigate overfitting. In particular, with strong masking-based regularization, MoEs are able to outperform dense models even when data is repeated more than 64 times. However, no method fully matches the performance of all-unique training data. Finally, we analyze internal mechanisms correlated with MoE overfitting in high repetition regimes, and find that MoE routing universally stabilizes early in training, and that expert specialization correlates with overfitting to repeated data. In sum, our work addresses the adverse interactions between sparsity and data repetition: we present evidence for the core mechanisms of overfitting and its potential remediation, and suggest promising avenues for future methods to reduce over-specialization in model parameters by disrupting memorization patterns.

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large foundation models. However, most MoE models use a fixed top-$k$ expert selection policy, assigning the same expert budget to every token even when fewer experts may be sufficient. Inference-time dynamic top-$k$ routing can reduce computation without retraining, but existing methods often overlook the distributional shift caused by deviating from the training-time routing configuration. We show that reducing the number of activated experts consistently increases the RMS scale and variance of SMoE outputs, inducing a representation mismatch that contributes to downstream performance degradation in addition to the loss of expert capacity. To address this correctable component, we propose Layer-wise Distribution Alignment (LDA), a lightweight inference-time correction that uses layer-wise calibration statistics to align reduced-routing representations with the default configuration. Across multiple SMoE LLMs, benchmarks, and routing strategies, LDA recovers much of the performance lost induced by the distributional shift under reduced routing while preserving sparse-inference efficiency with negligible overhead.

Directional ablation removes an aligned language model's ability to refuse by projecting a single "refusal direction" out of the weights that write the residual stream. It needs no gradient-based training and no optimization, only a few hundred contrastive prompts, which makes it the canonical white-box attack on open-weight alignment. However, it has been established only on dense models up to roughly 70B parameters. We study whether it survives the shift to frontier mixture-of-experts (MoE) models whose residual streams are no longer a single tensor and whose weights ship quantized. We apply it to GLM-5.3-Flash (320B parameters, 288 routed experts, a four-wide hyper-connection residual, block-FP8). The attack survives the architecture, but what it reaches is no longer where a reader of the original recipe would look for it. Editing the attention, dense and routed-expert writers on their own removes 0.039, 0.016 and 0.148 of refusal respectively; editing all three together removes 0.776. As a result, 74% of the effect exists only under the joint intervention. The part the conventional recipe reaches by module-name matching accounts for 0.066 of that 0.776, which is why it fails silently on an MoE. The effect does not follow from removing just any direction: ablating a random direction orthogonal to it leaves refusal unchanged. A category-concentrated residue survives every edit we tried: subspaces fitted on violence, sexual content and hate leave measurable refusal at every rank from 1 to 12. We report the method, the 41-89 percentage-point reductions it achieves across seven harmful benchmarks with no detected change in capability, and the boundary where it stops.

Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subsequent training. We show that this assumption can fail in a full 30B mixture-of-experts training pipeline. The checkpoints that perform better after the full downstream training stack also have higher solution density, i.e., retain downstream performance under local weight perturbations.

Designing foundation models for graphs is challenging due to the irregular structure of graphs and the different sizes and characteristics of embeddings. Chimaera integrates mixture-of-experts with graph foundation models (GFM). It integrates different GFM architectures, such as graph prompts and linear GNN models. Large language models are used to generate embeddings, and experts can be trained and combined following different strategies, GFMs, embeddings, etc. Furthermore, Chimaera extends existing linear GNNs to support link-level and graph-level tasks in addition to node-level tasks. Empirical analyses are performed on same-task and cross-task experiments with node, link, and graph classification tasks using six benchmark text-attributed graph datasets. The experiments demonstrate the effectiveness of Chimaera and its capabilities for transfer across tasks and datasets. Further insights include the need to use both large and small language models to generate embeddings for the experts, a strong cross-task transferability of simple but effective linear GNNs, and using few samples only to provide strong results.

Mixture-of-Experts (MoE) models expand model capacity without a proportional increase in training compute, but increasing sparsity makes reliable hyperparameter transfer challenging. In this work, we show that conventional hyperparameter scaling laws are insufficient for ultra-sparse MoEs: the optimal learning rate and batch size vary with activation ratio, and these shifts cannot be explained by either total or activated parameter count alone. To characterize this dependence, we conduct 1,800 pre-training runs spanning six activated-parameter scales and models with up to 6B total non-embedding parameters, processing approximately 20 trillion tokens at a cost of 200,000 equivalent H800 GPU-hours. Our results reconcile conflicting findings in prior work by revealing two scaling regimes. At fixed sparsity, the optimal batch size follows a power-law relationship with training tokens $D$, whereas the optimal learning rate scales with training compute $C$ and remains robust to the allocation between model size and data. Across sparsity levels, the activation ratio $A$ enters both relationships as an additional multiplicative power-law factor. These observations lead to unified hyperparameter scaling laws that transfer across MoE sparsity levels. Large-scale evaluation shows that the scaling form outperforms alternative functional forms. On a held-out ultra-sparse MoE with 12B total parameters and only 1/64 of its experts activated, the predicted hyperparameters remain close to the observed optima, supporting joint extrapolation across model scale and sparsity. Further experiments demonstrate transfer across expert granularities and isolate the effect of activation ratio from that of total expert count.

Universal multimodal embedding (UME) increasingly demands encoder's capacity for handling a broad range of tasks and modalities with increased complexity. Prior scaling methods either increase the representation size, retrieval effort, or scales the encoder into a heavy multimodal LLM. Recent works, such as Think-Then-Embed (TTE), explore scaling via reasoning tokens. However, embedding models are hard to scale up: increasing parameters directly tradeoffs for the large training batch size that contrastive learning needs, and retrieval has to be served under tight latency. Moreover, UME tasks are diverse in complexity, where scaling up embedders can bring significant redundant computation. In this work, we propose MOEMB, which instead scales UME along the expert axis through mixture-of-experts (MoE), growing encoder capacity while preserving single-vector, non-autoregressive encoding. Through a systematic study of the design space and training recipes for MoE-based UME, MoEMB sets a new state of the art on both MMEB-V2 and MRMR among models trained on public MMEB-family data: with only 3B active parameters, MoEMB surpasses TTE-based methods with >4x active parameters, using significantly less computes. To further improve the scalability and efficiency, we conduct the first comprehensive study of adaptive computation for MoE-based embedding, spanning diverse strategies across training-based and inference-only methods. Together, these results support expert scaling as an effective and efficient direction for UME, with adaptive computation further improving efficiency for MLLM-based embedding models towards large-scale retrieval and recommendation systems.

Mixture-of-Experts (MoE) pretraining relies on an auxiliary load-balancing loss (LBL) to drive per-expert utilization toward uniformity. Post-training inherits a different situation: the base router already encodes non-uniform expert co-activation structure, which a re-imposed uniformity objective flattens away. We show that downstream performance depends instead on holding this inherited routing softly, a principle we term soft router anchoring, and instantiate it as Router Prior Bias (RPB), a training-time bias that pulls the router logits toward a prior read off the frozen base router while leaving the router itself trainable. On math post-training of Moonlight-16B-A3B, RPB attains 45.77 in-domain accuracy against 31.91 under re-applied LBL and 29.44 under unanchored fine-tuning, and retains more out-of-domain capability than either. The ordering against LBL reproduces on a second model family (Qwen3-30B-A3B-Base), and the advantage over LBL is resolvable on an independently sourced corpus. Anchors defined on the router weights, on its logits, or on its output distribution perform comparably with no consistent ordering, which places the effect in the softness of the constraint rather than in the particular prior RPB supplies. Retained community structure in the expert co-activation graph tracks these gains wherever the base router is non-uniform enough for communities to form, yet enforcing the same prior as a hard assignment preserves that structure while performance falls sharply. Community structure is therefore a footprint of soft anchoring rather than its source, and the practical lesson is that inherited routing should be held softly during post-training, since both flattening it toward uniformity and enforcing it absolutely carry a downstream cost. Our code will be released at https://github.com/naver-ai/rpb.

Acidophilic proteins that remain stable and functional under highly acidic conditions, are important for industrial biocatalysis, acid-related bioprocessing, and the discovery of acid-stable enzymes. However, their identification relies heavily on time-consuming experimental screening methods. With the rapid growth of protein sequence databases, the need for computational identification methods that are both accurate and efficient has become stronger. The emergence of protein language models (PLMs) has significantly improved the sequence representation of downstream biological prediction tasks. This paper proposes MI-PEFT, a mixture-of-experts integrated parameter-efficient fine-tuning framework. Built on the ESM C-600M backbone, the framework incorporates LoRA-based PEFT methods and a DeepSeekMoE-based classification head to resolve the limitations of PEFT and significantly improve computational efficiency. Notably, this task is characterized by a significant class imbalance in the dataset, making high specificity particularly challenging. The experimental results demonstrate that MI-PEFT on PLMs, especially {\text{C}}^{\text{3}}\text{A}, serves as an efficient tool for identifying acidophilic proteins and a constrained pathway that helps resolve class-imbalance by preserving the pretrained representations.

Physics-informed neural networks (PINNs) struggle on PDEs whose governing physics varies across the domain. We trace this to a structural property of standard coordinate networks: their neural tangent kernel (NTK) is translation-variant and lets training points of large coordinate magnitude disproportionately influence predictions elsewhere, producing long-range coupling and gradient conflict during training. We show analytically and empirically that mixture-of-experts (MoE) architectures with centered, compact-support routers yield a uniformly banded NTK whose kernel-regression weights decay exponentially with distance, localizing the learning. Building on this, we propose \emph{Latent-MoE}, which interleaves domain-aware MoE blocks within a shared backbone. Unlike FB-PINNs or X-PINNs, which rigidly partition both the domain and the parameters so that the parameters on different subdomains are updated independently, Latent-MoE is designed to preserve the localization benefit of domain-aware routing while allowing capacity to flow across regions through the shared backbone. On standard homogeneous-physics benchmarks Latent-MoE is competitive with established baselines; on benchmarks with multi-stage time-variable physics, where global models and rigid domain decompositions both fall into spurious solutions, it improves over them by more than an order of magnitude, with markedly reduced gradient conflict during training.

Transformer surrogates for 3D flow prediction compress an industrial mesh into a small set of tokens from which every prediction point reads. Two operations follow: the retrieval step in which a point gathers information from the compressed representation, and the feed-forward layer that transforms what it retrieved. In current backbones both are blind to where the point sits in the flow. We condition both on wall-related physical signals. Distance-aware cross-attention (DA-CA) reshapes each volume query by its wall distance before retrieval, so that a point deep in the boundary layer draws different geometric information than one in the outer flow. Surface-volume mixture-of-experts (SVMoE) replaces the shared feed-forward layer with a small set of experts, routed by wall distance for volume points and by local geometry for surface points. Neither mechanism is tied to one architecture, so we apply both unchanged to AB-UPT and Transolver-3. On DrivAerML with 50 training cases, DA-CA reduces the volume pressure error by 10.1%, and DA-CA and SVMoE together reduce it by 12.5%; DA-CA improves the near-wall region at some cost in the far region, which SVMoE recovers, and the volume experts settle into near-wall, transition, and free-stream bands without routing supervision. Retrained on 300 cases, the conditioning improves every field quantity, reducing volume pressure and velocity errors by 33.1% and 18.6% on AB-UPT and by 21.4% and 21.3% on Transolver-3. Under Leave-One-Body-Out evaluation on DrivAerNet++, it reduces the volume pressure error on unseen body types by up to 14.2%.

Recent advances in Earth Observation representation learning accommodate heterogeneous sensors and missing observations, often through larger architectures. We present MEOX (Multimodal Earth Observation with eXperts), a multimodal masked autoencoder with a 2.939 million-parameter encoder and 3.115 million parameters in total. Sensor-specific adapters, explicit validity signals, and a shared sparse-expert block preserve modality-dependent processing before a learned patch-wise fusion. Four metadata tokens then accompany a single spatial sequence through fourteen further encoder blocks. Shared expert projections with private low-rank residuals constrain parameter growth, while rotary attention supports downstream spatial grids different from pretraining. The model is pretrained on 1.228 million MMEarth64 samples using modality-balanced masked reconstruction and structured sensor dropout. Frozen transfer is evaluated on six GEO-Bench tasks at both 64 and 224 pixels. The model reaches 64.42% mean intersection-over-union on cashew segmentation at 64 pixels and 90.56% average accuracy on EuroSAT at 224 pixels, exceeding the corresponding reported CSMoE results. BigEarthNet finetuning reaches 72.95% micro-average precision. Routing diagnostics distinguish expert participation, spatial dependence, modality association, and functional contribution. A held-out WorldCover probe measures a 0.64-percentage-point benefit from metadata, while retrieval separates same-sensor semantics from cross-sensor alignment. These results demonstrate sensor-flexible representation learning and strong task transfer using a compact parameter budget.

Mixture-of-experts (MoE) architectures increase model capacity by combining a collection of expert predictors through input-dependent routing, while often activating only a small subset of experts for each input. Despite their growing importance in modern large-scale models, the statistical roles of their design choices, especially routing, sparse activation, and shared experts, remain only partially understood, as existing theory has largely focused on parametric or correctly specified MoE models. In this paper, we view MoE as a form of localized aggregation and show how this localization reshapes the approximation-estimation-computation tradeoff. We derive oracle risk bounds for learning dense and sparse routing with evolving experts, separating approximation, expert-learning, and router-estimation errors, and characterize how sparse Top-K routing can retain the benefits of localized aggregation while controlling per-input computation. We also interpret gating through the geometry of input space, relating routing performance to regions of local expert advantage, and show how shared experts, as adopted in architectures such as DeepSeekMoE, can extract common predictive structure so that routed experts focus on residual local variation. Together, these results provide a unified statistical framework for understanding MoE through input-dependent expert aggregation, in which expert specialization and computational tradeoffs are governed by local predictive structure.

Large Language Models (LLMs) are revolutionizing digital communication by powering conversational agents deployed across domains such as customer service, digital sales, and insurance. These agents, built on LLMs, can understand user input, retrieve relevant information, and generate coherent responses. However, while they excel at factual communication, they often lack the ability to engage in truly persuasive, context-sensitive dialogue, especially in domains like insurance, where trust and clarity are critical. Building on this need within the insurance domain, our work focuses on improving the persuasiveness of digital agents, aka LLMs. To support this, we introduce InsureDial, a Persuasive Insurance Dialogue dataset, designed to capture the nuances of persuasive communication specific to motor insurance interactions. We introduce PersuaRL, a reinforcement learning-based framework that equips LLM-driven dialogue agents with the ability to adaptively explore, select, and coordinate strategies across multiple expert modules, guided by the evolving dialogue context, to achieve more effective persuasion. We conduct extensive automatic human and qualitative evaluations on two benchmark persuasion dialogue datasets, including our InsureDial. Our evaluations consistently demonstrate that PersuaRL outperforms baseline, generating contextually appropriate and highly persuasive responses.

In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting expert specialization. We show that contrasting each token against an Exponential Moving Average of the layer's hidden states, rather than routing on absolute magnitude, concentrates the routing signal onto a low-dimensional, highly separable subspace. Building on this, we propose the Contrastive Routing Mechanism (CoRM), which scores each expert by the gap between its affinity for the incoming token and its affinity for this shared reference state, interpreted through a distinct per-expert projection. The resulting experts have routing boundaries that align with linguistic structure significantly more than the Top-k baseline. Our experiments show that CoRM improves average zero-shot accuracy by +0.67 to +1.69 points (Top-1) and +1.38 to +1.77 points (Top-2) over standard Top-k MoE baselines on nine zero-shot reasoning benchmarks, at the minimal cost of 2.9% added parameters and 2.6% added FLOPs per token.

Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remains heavily constrained by the rigid, whole-expert abstraction. Existing frameworks manage, schedule, or prune experts as atomic execution units, which fixes the optimization boundary too early and leaves fine-grained intra-expert computational redundancy underexplored. In this work, we present PCoMoE, a path-compositional execution framework that shifts MoE inference from coarse-grained expert selection to fine-grained path composition. PCoMoE incorporates a path-level formulation of expert computation, a compatibility-aware layer-wise pruning strategy to suppress low-value path combinations, and a hardware-friendly execution engine to exploit reusable sub-expert structures under strictly bounded overheads. Experimental results demonstrate that PCoMoE achieves up to a 1.31x end-to-end inference speedup while enhancing model accuracy by 10%. The code is available at https://github.com/gzyyy0/PCoMoE

Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differently: multiple-choice predictions can change with option symbols or positions, while clinically plausible open answers can fail automated evaluation when serialization is malformed. We address both challenges with an answer-text memory, a permutation-stabilized vision--language expert, and a sparse candidate- expanding router. The cyclic schedule follows prior work; our contribution is to make expert top-2 a routable candidate alongside memory and expert top-1. On a 1,403-case retrospective internal analysis, this expansion improves a matched binary router from 88.95% to 91.73% (+2.78 percentage points; 95% CI 1.57--3.99), with 56 rescued errors and 17 regressions. Oracle coverage rises from 90.31% to 96.15%, and the final submitted configuration reaches 92.23% on the same retrospective split. For open questions, strict generation and deterministic guards produce 475/475 schema- valid participant-facing outputs without repair, retry, or hard-gate failure. Visual ablations reveal substantial textual dependence. Candidate expansion supplies the principal controlled routing gain; open-path evidence establishes output-contract validity rather than clinical correctness in medical use or deployment.

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.

Mixture-of-Experts (MoE) models enable efficient scaling of large language model (LLM) inference but suffer from substantial data-movement overhead when deployed on neural processing unit (NPU)-based systems. Near-Data Processing (NDP) provides a promising way to mitigate this bottleneck via cooperative NPU-NDP execution. However, existing NPU-NDP MoE systems do not fully account for hardware heterogeneity, dynamic expert-level concurrency, and temporal expert reuse during batched inference. This paper presents DynaNDE, a dynamic near-data expert scheduling framework that exploits NPU-NDP collaboration to accelerate batched MoE inference. DynaNDE introduces an analytical performance model that captures hardware heterogeneity, data-movement costs, and communication-computation overlap in cooperative NPU-NDP execution. Guided by this model, DynaNDE determines per-layer expert scheduling across the NPU and NDP while accounting for expert-level concurrency. DynaNDE also incorporates a reuse-aware runtime that avoids redundant parameter movement when experts reside in NPU memory. Experimental results show that DynaNDE achieves substantial throughput improvements over the state-of-the-art NPU-NDP MoE serving framework, with average speedups of 2.6$\times$ and 2.2$\times$ for the prefill and decoding stages, respectively.

Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traffic demand, and radio conditions challenge the scalability of conventional radio resource management (RRM). While offline reinforcement learning (RL) methods have demonstrated strong decision-making capabilities, learning a single policy that performs consistently across heterogeneous wireless environments remains difficult due to conflicting optimization objectives and limited model specialization. These challenges become particularly pronounced in coordinated multipoint (CoMP) transmission, where selecting the optimal serving-cell combination requires sequential decision-making under evolving network conditions. This paper presents the Wireless Sparse Decision Transformer with Mixture of Experts (WiSDoM), a sparse multi-task offline RL framework for adaptive multi-cell selection. WiSDoM combines Decision Transformers (DTs) with a Mixture-of-Experts (MoE) architecture that dynamically activates specialized experts according to task characteristics. This MoE mechanism improves model capacity without proportionally increasing inference cost, mitigates negative transfer, and enables expert specialization across tasks. WiSDoM is trained jointly on diverse network configurations spanning multiple base station and user equipment densities, mobility levels, and scheduler policies. Experimental results show that WiSDoM consistently outperforms heuristic methods, single-task models, and conventional multi-task DTs, improving quality of experience (QoE) by up to 55% while activating approximately one-third of the parameters of its dense counterpart during inference. Furthermore, WiSDoM exhibits strong task generalization and efficiently adapts to unseen wireless scenarios through few-shot prompting without retraining or fine-tuning.

Multimodal Sentiment Analysis (MSA) is a fundamental component of affective computing that aims to decipher complex emotional states by integrating verbal content with non-verbal cues including vocal intonation and facial micro-expressions. While recent disentanglement-based approaches have advanced the field, their potential is hindered by two methodological challenges. First, static computation graphs process all samples indiscriminately regardless of semantic complexity, which leads to suboptimal representation for diverse emotional expressions and contextual scenarios. Second, generic contrastive objectives often neglect the intrinsic ordinal hierarchy of sentiment intensities. To systematically address these limitations, we introduce Multimodal Adaptive Expert Selection with Text Routing and Ordinal prototype optimization (MAESTRO), a novel framework designed to dynamically orchestrate and refine multimodal representations. Drawing inspiration from an orchestra conductor, we design a Text-Guided Hybrid Mixture-of-Experts (MoE) mechanism. Unlike static fusion, this module utilizes linguistic context as a routing signal to dynamically activate specific audio-visual experts, thereby resolving cross-modal ambiguity through adaptive feature enhancement. Furthermore, to capture fine-grained sentiment gradations, we propose an Ordinal-aware Prototype Contrastive Learning (O-PCL). By incorporating distance-based penalties into the prototype learning objective, O-PCL enforces a structured latent space that preserves the natural order of emotion. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that MAESTRO achieves state-of-the-art performance, and qualitative analysis further confirms the interpretability of our dynamic routing paradigm.

We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-context and latency-sensitive physical AI applications. The model adopts Quantile Routing in a dynamic top-k configuration, enabling token-adaptive expert allocation while maintaining balanced expert utilization and a controlled average compute budget. During deployment, we further apply capacity-constrained routing to prompt prefill for more regular and efficient expert execution, while retaining dropless routing during pretraining. Turing-20B-A2B also employs a hybrid attention architecture that combines Lightning Attention with a small number of full-attention layers for efficient long-context modeling. The model is pretrained with a progressive three-stage curriculum and extended to a native context length of 128K through continued pretraining, with further inference-time extension to 512K using YaRN. Despite its compact active-parameter budget, Turing-20B-A2B achieves, at the base-model stage, overall general capability exceeding Qwen3-8B Base and approaching Qwen3.5-9B Base, while maintaining strong long-context performance and favorable prefill-latency scaling. These results demonstrate an effective balance among model capability, long-context scalability, and practical inference efficiency.

Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-induced quality loss under a fixed budget, but Mixture-of-Experts (MoE) models contain these layers in every expert of every MoE block, so the allocation space grows far larger than in a dense model. Existing methods either allocate within each block under a uniform per-block budget, or allocate across blocks through an additive proxy, and neither directly optimizes a model-level objective over the choices that couple the blocks. We propose Q-Strata, a bi-level allocator that ranks within-block assignments with a cheap proxy and allocates across blocks with a model-level objective evaluated on the assembled quantized model. Its inner stage caches a Pareto frontier of candidates per block over finely spaced budgets, leaving the outer stage to set one budget per block instead of a bitwidth for every linear layer. With the search reduced to one budget per block, the outer stage optimizes this model-level objective directly, capturing the inter-block coupling that additive proxies miss. On Mixtral-8x7B-Instruct, Qwen1.5-MoE-A2.7B, and DeepSeek-V2-Lite, Q-Strata consistently achieves lower WikiText2 perplexity than uniform-bitwidth GPTQ and the state-of-the-art MoE MPQ methods MxMoE and GEMQ in the low-bit regime. The code is available at https://github.com/snu-mllab/Q-Strata/tree/main.

Click-through rate (CTR) models vary in feature-interaction design, yet their top networks usually remain a single multilayer perceptron shared by all examples. Heterogeneous user, item, and context subgroups therefore update the same parameters; weakly aligned learning signals make the aggregate gradient a compromise among competing directions. We study the competition on Avazu with 4 models and 4 semantic fields. Across all architectures, semantic subgroups show lower Top-NN gradient cosine similarity than random groups matched by sample size and label ratio, with reductions of 0.23-0.37. This competition motivates input-conditioned experts, but directly replacing an established Dense mapping changes its initial function, sharing pattern, and capacity, obscuring the source of gains. We introduce PRIME (Plug-in Residual Input-conditioned Mixture of Experts), a Dense-anchored mixture of low-rank residual experts. PRIME anchors the original prediction and uses zero-residual initialization to match the Dense baseline exactly at training onset. Input-dependent routing weights low-rank experts for example-specific logit corrections; multi-bag aggregation and EMA load biases stabilize conditional estimation. We evaluate PRIME on held-out Avazu and Criteo test sets across 13 CTR architectures and five paired seeds. Median paired AUC gains are +0.0022 and +0.0066, with LogLoss reductions of 0.0011 and 0.0081, respectively. On FiBiNET and DCNv2, PRIME outperforms APG in all ten seed-level AUC comparisons while using fewer parameters and lower inference latency on both backbones. These results show that function-preserving conditional residuals add input-dependent capacity while preserving the Dense path and its optimization stability. Code is available at https://github.com/YH-learning/PRIME.

We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE) language model trained from scratch as a high-performance foundation for \emph{agentic} applications. Trained on approximately 8.5T tokens---fewer than its predecessor, A.X K1---on a smaller but higher-quality mixture with substantially expanded agentic and software-engineering data, it nonetheless improves over A.X K1 across the board, by over 30 percentage points on some benchmarks, reflecting large gains in token efficiency. To support long contexts efficiently, we introduce Sparse Gated Attention (SGA), which combines sparse attention with gated attention, and adopt Gated Norm (GN) to stabilize large-scale training. SGA is trained natively at 128K through a \emph{sparse} indexer warmup that optimizes the indexer against its own sparse top-$k$ selection rather than the dense attention distribution, making adaptation markedly cheaper: each query reads only 2,048 positions, yet long-context quality is unchanged and A.X K2 scores 94.6 on RULER out to 256K. The outlier suppression of GN in turn keeps 4-bit NVFP4 serving within one point of FP8 accuracy. A simple yet effective Think-Fusion recipe further lets users switch between thinking and non-thinking modes within a single unified model. Extensive evaluations show that A.X K2 performs competitively against strong open-weight baselines, matching or exceeding them on math and Korean-language benchmarks.

Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on both user preferences and input prompts, controllable multi-objective generation must dynamically adapt models at inference time without retraining. To address this, we propose Evolutionary Soups, a mixture-of-experts framework for fine-grained generation control, with gating networks trained via an evolutionary algorithm. The per-layer gating networks dynamically produce expert-merging coefficients from hidden-state representations, while the evolutionary algorithm incorporates greedy hypervolume contribution for effective evolution of these gating networks, achieving consistent improvements on large and noisy training datasets and broader coverage of the non-convex Pareto front. Experiments across three tasks demonstrate the effectiveness of Evolutionary Soups over baselines: it achieves the best hypervolume, linear utility, and Tchebyshev utility (~20% improvement) among controllable methods on all tasks.

Neural Architecture Search (NAS) has so far rarely been applied to Mixture-of-Experts (MoE) models, and existing MoE designs leave the alignment between experts and the structure of the data to emerge on its own. We propose an architecture search framework that makes this alignment an explicit search variable: the assignment of data clusters to experts is optimised jointly with the per-expert architectures. We cast the joint problem as a cluster-aware likelihood maximisation, show that it coincides with the incomplete-data maximum likelihood of a latent-variable mixture, and solve it by a generalised Expectation-Maximisation procedure whose otherwise intractable expert-quality term is supplied by an adaptively refined surrogate. We prove that the iterates converge whenever the surrogate errors are summable, and that at every limit point no candidate the search produces improves the true objective. On a heterogeneous image-classification mixture the method recovers the underlying domain partition on 95% of clusters without ever observing domain labels, and on that benchmark and a four-domain time-series forecasting one alike it outperforms the MoE and NAS baselines that likewise use no label information.

As large language models (LLMs) continue to scale, parameter-efficient fine-tuning (PEFT) has become a practical alternative to full-parameter adaptation. Prompt tuning is effective, but existing approaches either use flat prompt structures or hierarchical structures with fixed prompt composition, limiting adaptive prompt specialization. To address this limitation, we propose HiVe, a prompt tuning framework that models prompts at multiple levels and enables input-dependent specialization. HiVe constructs a prompt hierarchy by leveraging inter-task relationships during training, and employs a vertical mixture-of-experts (V-MoE) mechanism at inference time to compose prompts up to the level of specialization required for each input. Experiments show that HiVe consistently outperforms strong prompt tuning baselines across diverse tasks.

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.

Fine-grained human action recognition (FHAR) must distinguish visually similar actions that differ mainly in body configuration, timing, or local appearance. RGB representations retain visual context but often suppress joint-level geometry, whereas skeleton representations encode kinematics but discard dense spatial detail. We introduce FineX, which factorizes fine-grained cues into RGB appearance, pose heatmap geometry, and skeletal-graph topology. Pairwise cross-attention enables symmetric, stream-preserving information exchange, followed by a streamwise latent sparse Mixture-of-Experts that routes each representation to a content-dependent subset of shared experts, regularized by a load-balancing objective. FineX achieves state-of-the-art results on Gym99, Gym288, and Diving48. On the long-tailed Gym288, it raises mean class accuracy from 68.6% to 76.2% (+7.6 points) without textual supervision or large-scale vision-language pre-training, demonstrating the benefit of structured visual-pose-graph fusion and conditional expert refinement for FHAR.

Financial volatility is regime dependent, yet incorporating regime information into neural networks can also destabilize training. This paper asks where such information should enter a neural cross-sectional volatility forecasting model. We study five-day realized-volatility forecasts for 1,027 U.S. equities using a rolling walk-forward evaluation framework in which information, model capacity, hyperparameter tuning, and random seeds are matched across architectures. We propose RG-ResMoE, a regime-gated residual mixture-of-experts architecture in which regime information is used only for expert routing rather than for direct forecasting. The base predictor models volatility from stock features, while a gating network uses regime state variables to route residual corrections. RG-ResMoE consistently outperforms a capacity-matched MLP in both forecasting accuracy and training stability in the main U.S. study. Similar gains are observed on an independent Japanese panel. The integration pathway is decisive: appending the same regime variables directly to the forecasting input degrades both predictive performance and training stability, whereas restricting them to the routing gate improves accuracy and Value-at-Risk calibration. Hard routing consistently underperforms soft routing. The results suggest that, in compact neural volatility forecasting models, the primary value of mixture-of-experts models lies less in increasing model capacity than in controlling how nonstationary regime information influences prediction.

Training Mixture-of-Experts (MoE) models for reinforcement learning (RL) couples two load-balancing problems: sequence composition determines dense attention work in each data-parallel microbatch, while token routing determines sparse expert work on expert-parallel ranks. Optimizing either alone can shift the bottleneck to the other. In MoE RL, rollout-time routing replay exposes every sample's sequence length and layer-wise expert demand before its training step. We present RoutePack, a hierarchical planner that coordinates state-consistent, layer-wise expert rerouting with joint attention- and expert-aware data packing over an optimizer-step window. RoutePack first places experts independently at each MoE layer using aggregate routing demand. It then packs samples into the smallest certified, or best-known feasible, number of token-capped execution rows and optimizes their DP layout with a projected EDP-shard-aware objective. The objective combines a window-normalized linear-quadratic attention proxy with per-layer physical EP-rank peaks and minimizes the accumulated cost of the slowest EDP shard. Parallel population annealing searches fixed-row feasible layouts while preserving sample coverage, capacity, nonempty cells, equal microbatch counts, and communicator topology. State-consistent materialization preserves logical top-k routing and existing MoE kernels without microbatch-level expert replication. Across Ling-3.0-Tiny and Ling-3.0-Flash, expert rerouting improves mean trainer-measured token throughput by 3.80% and 10.50%, while routing-aware packing adds another 4.86% and 3.98%, respectively. Overall, RoutePack improves throughput by 8.85% and 14.89% over the baseline.

Mixture-of-Experts (MoE) models are attractive for edge deployment because they provide high model capacity while activating only a small subset of parameters per token, improving compute efficiency. However, MoE inference at the edge is fundamentally limited by memory. Expert parameters are large and often reside in off-chip memory due to capacity, cost, and power constraints, putting expert loading to the critical path. We present APEX: Adaptive Expert Prefetching, a predictive resource management framework that overlaps expert loading with useful computation. APEX introduces a lightweight prefetch router that predicts candidate experts before the attention block to dynamically fetch additional experts using a learned confidence model. This adaptive strategy achieves over 99% overlap accuracy, significantly outperforming fixed top-k prefetching techniques. APEX supports two execution modes: a correctness-preserving mode that guarantees exact routing semantics, and a stall-free mode that eliminates residual stalls by operating on available experts with negligible impact on application accuracy. Across multiple MoE models, the correctness-preserving mode reduces per-token latency by up to 26% and improves energy-delay product (EDP) by up to 41% over state-of-the-art baselines, while the stall-free mode provides additional efficiency gains with negligible impact on application accuracy. These results establish adaptive, confidence-driven expert prefetching as an effective approach for efficient MoE inference on edge systems.

Recent advances in Large Language Models (LLMs) have spurred cross-modal solutions for time-series forecasting. However, existing methods rely heavily on textual prompts for modality alignment-introducing nontrivial computational overhead and failing to leverage the rich spectral dynamics inherent in time-series data. To enable prompt-free, frequency-aware adaptation of frozen LLMs, we propose FM-LLM (Frequency-Enhanced Mixture-of-Experts for adapting LLMs to Time Series Forecasting), an autoregressive framework grounded in constrained asymmetric coupling. A Fourier Analysis Network (FAN)-based spectral token aligner injects structured harmonic representations directly into the frozen LLM with numerical compatibility. An asymmetric Mixture-of-Experts (MoE) decoder enforces role separation: shared experts with lightweight FAN layers reconstruct the global periodic backbone, while routed experts-restricted to standard FFNs-specialize in modeling non-periodic residual dynamics. A time-frequency hybrid loss function jointly optimizes temporal accuracy and spectral consistency, mitigating error accumulation during long-horizon autoregressive rollouts. Evaluated across eleven public benchmarks, FM-LLM achieves state-of-the-art performance on 59 out of 78 evaluation metrics. Compared to the strongest autoregressive LLM-based baseline, it delivers average improvements of 5.3% in MSE and 5.6% in MAE, with maximum gains reaching 8.0% for MSE and 8.4% for MAE. FM-LLM also demonstrates robust transferability, maintaining superior performance in 10% few-shot and zero-shot forecasting scenarios.

Long-tailed classification poses a reliability challenge because models trained on imbalanced data are unevenly reliable across frequent and underrepresented classes. While existing methods address imbalance through re-balancing, adjustment, representation learning, or multi-expert modeling, they rarely estimate which expert should be trusted for each class. This paper proposes CLEAR (Class-wise reLiability-aware Expert Aggregation for long-tailed Recognition), a modular ensemble framework for long-tailed classification. CLEAR generates diverse experts through threshold-based structured sampling while preserving the full label space, then estimates a class-wise trust score for each expert using a smoothed class-wise precision formulation. During inference, expert predictions are combined through class-wise generalized product-of-experts aggregation, allowing different experts to be emphasized for different classes. Experiments on CIFAR-100-LT, ImageNet-LT, and Places-LT across multiple backbones show that CLEAR achieves competitive overall accuracy and particularly strong few-shot performance. These results support class-wise expert reliability as a useful design principle for long-tailed ensemble learning.

Gradient-free post-training has emerged as a compelling alternative to gradient-based optimization for large language models (LLMs), but existing approaches remain costly. We ask whether structured search can identify a strong single expert under a modest evaluation budget. Motivated by evidence that useful weight updates lie in low-dimensional subspaces, we apply Bayesian optimization within a random linear embedding of weight space. Our method requires no backpropagation and uses a Gaussian process surrogate to guide candidate evaluations efficiently. Across several reasoning benchmarks with Qwen2.5-Instruct models from 0.5B to 3B parameters, Bayesian optimization using five times less candidate evaluations matches or exceeds RandOpt. These results show that surrogate-guided search can substantially reduce the evaluation cost of gradient-free post-training while producing stronger deployable single experts.

Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead. In practice, factors such as framework adaptation, numerical precision, and operator implementation can cause failures, including gradient overflow and loss divergence. Reproducing such failures directly on large models requires considerable time and computational resources. This paper systematically analyzes failures encountered during large-scale RL training on the Huawei Ascend platform, summarizes representative failure types, and identifies three model-side factors relevant to fault reproduction. Based on these factors, we propose a proxy-model construction method for low-cost fault investigation and auxiliary diagnosis. It employs structure-preserving, clustering-based expert pruning to select representative experts while retaining the model's backbone architecture, routing mechanism, and basic task capabilities. Our experimental results show that the proxy models reduce accelerator requirements by 50%-87.5% and achieve up to a 33.3x reduction in per-step NPU-hour cost, while preserving major training dynamics and reproducing fault responses consistent with the original models. Overall, the proxy models can serve as low-cost surrogates for fault reproduction, targeted validation, and auxiliary diagnosis in RL post-training.

In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage selects an architecture and training recipe, optimizing loss under compute constraints, and a separate systems stage then optimizes the implementation for hardware efficiency. In this work, we develop MOSAIC, which formulates model architecture and systems co-design as an optimization problem. MOSAIC couples a predictive scaling law with a calibrated performance model that estimates Model FLOPs Utilization (MFU), communication cost, memory footprint, and the best parallel layout. We instantiate the framework for sparse Mixture-of-Experts (MoE) language models, where expert count, routing sparsity, and other MoE layer dimensions affect both the loss and systems efficiency. We fit a scaling law on sparse MoE models trained on text data, whose scaling dimensions include the sparsity factor, which is the fraction of model parameters inactive per token in a forward pass. The scaling law sweeps in our work span active parameters from $104$ million to $2.7$ billion and total model sizes reaching $79$ billion parameters. We show that, within the calibrated sparsity range, an efficiency-agnostic model-FLOPs budget admits no interior optimal sparsity. The fitted loss decreases monotonically with sparser models and the compute optimum lies at the upper boundary of the data support. An optimal sparsity in MoE models instead emerges under the cluster's systems constraints, as captured by MOSAIC. Our results argue for a shift towards unified architecture and systems co-design for frontier language model training.

Breast lesion detection in mammography remains a challenging task due to variations in image quality, lesion appearance, and population demographics across datasets. While current object detectors such as YOLO and DETR achieve strong results on individual datasets, their performance often degrades when trained on or applied across heterogeneous sources. To address this, we propose MammoMix, a novel framework based on Mixture-of-Experts (MoE) paradigm for robust and generalizable lesion detection. In MammoMix, each expert model is trained on a specific domain, allowing it to specialize in distinct characteristics of its source data. A gating mechanism adaptively weighs contributions from each expert based on input image, combining their outputs to enable domain-adaptive inference. To improve reliability, we further incorporate a calibration module, MoCAE, which adjusts confidence scores to reflect true predictive uncertainty. We evaluate MammoMix on 3 public mammography datasets: CSAW, DDSM, and DMID, covering diverse clinical settings. Results show that MammoMix outperforms baseline detectors in both average precision and reliability, particularly on datasets with greater variability. Our findings demonstrate that expert specialization and calibrated ensemble fusion significantly enhance model generalization and robustness. MammoMix offers a promising step toward dependable AI-assisted breast cancer screening across real-world clinical domains.

Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowledge, fine-grained methods vary computation within experts, and dynamic routers adapt the number of active experts. Yet these decisions are usually made independently, overlooking a basic dependency: extracting reusable computation changes both what remains and how much expert capacity the remainder needs. We study this dependency by decomposing sparsely upcycled feed-forward experts into key-value channels. Co-activated experts align at a subset of value positions; removing these positions changes expert preference; and greater shared coverage is associated with lower residual expert demand. These observations lead to one principle: share first, then route what remains. We instantiate it in UniF-MoE, a unified framework for token-adaptive MoE computation. Each expert is partitioned into aligned blocks. A shared-demand score sets the shared block count and pathway weight, key prototypes select the shared content, and the complementary demand determines the residual expert count through cumulative routing mass. A Gram regularizer separates and normalizes router embeddings, promoting diverse routing directions, sparse expert overlap, and a simple routing geometry. Experiments on DomainBed and GLUE show that this unified design improves predictive performance over representative static and dynamic MoEs while reducing activated computation, inference latency, and memory. Code is available at https://github.com/existence0420/UniF-MoE.

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.

Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation to every image regardless of the underlying disease distribution. We propose a novel architecture that resolves this via sparse conditional computation, pairing a Guided Context Gating (GCG) spatial attention front-end with a sparsely-routed Mixture-of-Experts (MoE) block operating over feature tokens. Crucially, this routing yields an interpretable, data-driven decomposition. Expert allocation is significantly disease-dependent (p < 0.001), with the healthy Normal state and morphologically distinct pathologies (e.g., ERM, AMD) isolating to dedicated experts. On a five-class, patient-disjoint 5-fold cross-validation benchmark, our model achieves 0.912 +/- 0.008 macro AUC and 0.653 +/- 0.014 macro F1. Furthermore, Grad-CAM++ and post-MoE t-SNE visualizations confirm that expert routing aligns with localized lesions and geometrically maps co-occurring cases between their constituent clusters, positioning sparse MoE as an interpretable approach to multi-disease retinal screening.

Text-conditioned general audio generation is moving beyond isolated speech, music, and sound-effect synthesis toward a single model that can compose them into controllable, coherent audio scenes. This unified setting is particularly challenging: heterogeneous components impose conflicting structural requirements on a shared backbone, while a complex mixed scene may contain locally distinct or overlapping content that demands fine-grained adaptation within the same clip. Existing audio mixture-of-experts (MoEs) mainly route at the domain level, while token-wise routing overlooks the local continuity inherent to acoustic signals. We propose SonicWeave, a flow-matching model for unified audio scene generation. At its core is a chunk-routed MoE with a conflict-gated prior-evidence routing mechanism (CPE-MoE). CPE-MoE routes contiguous acoustic chunks by combining a global prior that encodes the structured text condition and diffusion phase with local evidence from the evolving acoustic state. A learned conflict gate favors the prior when local states are unreliable, while allowing local evidence to influence routing when a region departs from the global scene context. SonicWeave supports speech, music, sound effects, singing, and their fine-grained mixtures with a single set of weights. Across TTS, TTA, and TTM benchmarks, SonicWeave consistently improves over controlled Dense and Base-MoE baselines. Complex-scene evaluation further demonstrates improved compositional quality, while routing analyses reveal content-dependent expert specialization across diffusion phases. These results suggest that temporally coherent, prior-evidence routing is an effective conditional-computation strategy for unified audio generation. Project page: https://caiyunrui.github.io/SonicWeave.

State Space Models (SSMs), as a mainstream research direction of linear Transformers, aim to achieve higher efficiency than standard Transformers in long-context modeling. However, existing SSMs suffer from limited input adaptivity and constrained memory capacity, leading to information loss when modeling ultra-long sequences. To address these limitations, we propose MixFormer, a novel linear Transformer that integrates a Mixture-of-Memory-Experts (MoE) mechanism. Specifically, the model maintains differentiated memory states through multiple collaborating memory experts and employs a novel Time-Aware Linear Attention (TALA) mechanism, which leverages learnable exponential decay functions and positional biases to dynamically update memory. This design enables the model to selectively reinforce important historical information while effectively mitigating memory dilution, substantially improving long-range dependency modeling. Experiments on long-sequence text and image generation tasks demonstrate that MixFormer not only achieves significant performance gains but also provides a more sustainable computational backbone for the next generation of web infrastructure.

Dense expert merging combines domain-specialized language models into one single checkpoint, typically by admitting task-vector support in weight space. However, this admission is governed by three decisions that existing methods answer only partially: where to open layer capacity from cross-expert conflict, who should occupy that capacity based on domain demand, and how to admit the resulting support without relying on costly recipe search. To tackle these issues, we propose SigMerge (Signature-Guided Capacity Occupancy), a structured capacity assignment framework for dense expert merging. Starting from a dense base merge, conflict signatures set each layer's capacity from cross-expert conflict, positive base-merge deficits set each domain's share of that capacity, and a sequential occupancy rule admits each expert delta up to the resulting layer-domain budget. Across 21 paired settings spanning seven dense base merges and three model pools, SigMerge improves every one (by 15.0% on average) and achieves the best average rank (1.67) among six merging methods, outperforming three categories of merging baselines.