{"total":205,"rows":[{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040,"area":"moe"},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572,"area":"mllm"},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2510.10274","title":"X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model","created":"2025-10-11","cited_by_count":303,"area":"vla"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2605.26494","title":"The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence","created":"2026-05-26","cited_by_count":61,"area":"agents"},{"id":"2509.01322","title":"LongCat-Flash Technical Report","created":"2025-09-01","cited_by_count":58,"area":"agents"},{"id":"2501.11873","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","created":"2025-01-21","cited_by_count":54,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31,"area":"moe"},{"id":"2506.14038","title":"Load Balancing Mixture of Experts with Similarity Preserving Routers","created":"2025-06-16","cited_by_count":22,"area":"moe"},{"id":"2512.14080","title":"SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations","created":"2025-12-16","cited_by_count":21,"area":"moe"},{"id":"2507.20776","title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","created":"2025-07-28","cited_by_count":20,"area":null},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"id":"2503.16057","title":"Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts","created":"2025-03-20","cited_by_count":14,"area":"diffusion"},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2601.18089","title":"LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts","created":"2026-01-26","cited_by_count":14,"area":"moe"},{"id":"2501.15103","title":"Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning","created":"2025-01-25","cited_by_count":13,"area":"moe"},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2604.09780","title":"The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise","created":"2026-04-10","cited_by_count":13,"area":"moe"},{"id":"2508.19594","title":"Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs","created":"2025-08-27","cited_by_count":12,"area":"moe"},{"id":"2601.10639","title":"STEM: Scaling Transformers with Embedding Modules","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2603.28743","title":"Rethinking Language Model Scaling under Transferable Hypersphere Optimization","created":"2026-03-30","cited_by_count":12,"area":"lr"},{"id":"2505.20524","title":"Towards Fully FP8 GEMM LLM Training at Scale","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2509.21892","title":"Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts","created":"2025-09-26","cited_by_count":11,"area":"moe"},{"id":"2512.23447","title":"Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss","created":"2025-12-29","cited_by_count":11,"area":"moe"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2504.12463","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","created":"2025-04-16","cited_by_count":10,"area":"moe"},{"id":"2508.02853","title":"Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives","created":"2025-08-04","cited_by_count":10,"area":"moe"},{"id":"2508.15281","title":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2509.25278","title":"MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series","created":"2025-09-29","cited_by_count":10,"area":"moe"},{"id":"2510.17483","title":"ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts","created":"2025-10-20","cited_by_count":10,"area":"moe"},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2511.05007","title":"MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2605.07260","title":"When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models","created":"2026-05-08","cited_by_count":9,"area":"moe"},{"id":"2606.04101","title":"UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing","created":"2026-06-02","cited_by_count":9,"area":"moe"},{"id":"2501.13074","title":"Autonomy-of-Experts Models","created":"2025-01-22","cited_by_count":7,"area":"moe"},{"id":"2507.23620","title":"DivControl: Knowledge Diversion for Controllable Image Generation","created":"2025-07-31","cited_by_count":7,"area":"diffusion"},{"id":"2509.23933","title":"Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms","created":"2025-09-28","cited_by_count":7,"area":"moe"},{"id":"2511.10971","title":"ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization","created":"2025-11-14","cited_by_count":7,"area":"moe"},{"id":"2512.01252","title":"Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe","created":"2025-12-01","cited_by_count":7,"area":"moe"},{"id":"2411.00918","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","created":"2024-11-01","cited_by_count":6,"area":"moe"},{"id":"2503.05447","title":"Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts","created":"2025-03-07","cited_by_count":6,"area":"moe"},{"id":"2507.08771","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","created":"2025-07-11","cited_by_count":6,"area":"moe"},{"id":"2509.25913","title":"Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel","created":"2025-09-30","cited_by_count":6,"area":"moe"},{"id":"2510.23027","title":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","created":"2025-10-27","cited_by_count":6,"area":"lr"},{"id":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"area":"moe"},{"id":"2601.18664","title":"S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation","created":"2026-01-26","cited_by_count":6,"area":"lr"},{"id":"2603.05806","title":"MoE Lens -- An Expert Is All You Need","created":"2026-03-06","cited_by_count":6,"area":"moe"},{"id":"2503.05029","title":"Continual Pre-training of MoEs: How robust is your router?","created":"2025-03-06","cited_by_count":5,"area":"moe"},{"id":"2504.19925","title":"SYMI: Efficient Mixture-of-Experts Training via Model and Optimizer State Decoupling","created":"2025-04-28","cited_by_count":5,"area":"moe"},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.05767","title":"dots.llm1 Technical Report","created":"2025-06-06","cited_by_count":5,"area":"moe"},{"id":"2510.03293","title":"From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts Routing","created":"2025-09-29","cited_by_count":5,"area":"moe"},{"id":"2512.07628","title":"MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2603.06626","title":"Grouter: Decoupling Routing from Representation for Accelerated MoE Training","created":"2026-02-22","cited_by_count":5,"area":"moe"},{"id":"2605.15403","title":"$\\phi$-Balancing for Mixture-of-Experts Training","created":"2026-05-14","cited_by_count":5,"area":"moe"},{"id":"2506.07366","title":"MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing","created":"2025-06-09","cited_by_count":4,"area":"moe"},{"id":"2511.10676","title":"Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models","created":"2025-11-10","cited_by_count":4,"area":"moe"},{"id":"2512.16144","title":"INTELLECT-3: Technical Report","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"id":"2602.00509","title":"PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching","created":"2026-01-31","cited_by_count":4,"area":"moe"},{"id":"2603.00054","title":"Expert Divergence Learning for MoE-based Language Models","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2604.04230","title":"Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training","created":"2026-04-05","cited_by_count":4,"area":"moe"},{"id":"2605.12476","title":"Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts","created":"2026-05-12","cited_by_count":4,"area":"moe"},{"id":"2606.14957","title":"Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2503.11486","title":"A Review of DeepSeek Models' Key Innovative Techniques","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2505.19525","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","created":"2025-05-26","cited_by_count":3,"area":"moe"},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2508.02002","title":"Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization","created":"2025-08-04","cited_by_count":3,"area":"moe"},{"id":"2510.16138","title":"Expert Merging in Sparse Mixture of Experts with Nash Bargaining","created":"2025-10-17","cited_by_count":3,"area":"moe"},{"id":"2510.16448","title":"Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts","created":"2025-10-18","cited_by_count":3,"area":"mllm"},{"id":"2511.23319","title":"Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2603.11535","title":"Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing","created":"2026-03-12","cited_by_count":3,"area":"moe"},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2604.01622","title":"Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models","created":"2026-04-02","cited_by_count":3,"area":"diffusion"},{"id":"2605.02641","title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","created":"2026-05-04","cited_by_count":3,"area":"moe"},{"id":"2605.08292","title":"Hierarchical Mixture-of-Experts with Two-Stage Optimization","created":"2026-05-08","cited_by_count":3,"area":"moe"},{"id":"2605.27081","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2605.27358","title":"MobileMoE: Scaling On-Device Mixture of Experts","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2606.01062","title":"DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts","created":"2026-05-31","cited_by_count":3,"area":"moe"},{"id":"2606.25971","title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","created":"2026-06-24","cited_by_count":3,"area":"moe"},{"id":"2607.28611","title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers","created":"2026-07-30","cited_by_count":3,"area":"diffusion"},{"id":"2505.04075","title":"Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress","created":"2025-05-07","cited_by_count":2,"area":"lr"},{"id":"2506.02890","title":"Scaling Fine-Grained MoE Beyond 50B Parameters: Empirical Evaluation and Practical Insights","created":"2025-06-03","cited_by_count":2,"area":"moe"},{"id":"2507.10618","title":"Compute Requirements for Algorithmic Innovation in Frontier AI Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2508.01261","title":"Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language Models","created":"2025-08-02","cited_by_count":2,"area":"moe"},{"id":"2509.06346","title":"Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing","created":"2025-09-08","cited_by_count":2,"area":"moe"},{"id":"2510.01185","title":"Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs","created":"2025-10-01","cited_by_count":2,"area":"moe"},{"id":"2512.16248","title":"Sigma-MoE-Tiny Technical Report","created":"2025-12-18","cited_by_count":2,"area":"moe"},{"id":"2512.23070","title":"FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment for Edge Computing","created":"2025-12-28","cited_by_count":2,"area":"moe"},{"id":"2601.00457","title":"Geometric Regularization in Mixture-of-Experts: The Disconnect Between Weights and Activations","created":"2026-01-01","cited_by_count":2,"area":"moe"}],"next_cursor":"100"}