{"total":61,"rows":[{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"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":"2509.03498","title":"OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation","created":"2025-09-03","cited_by_count":50,"area":"moe"},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35,"area":"moe"},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2502.05172","title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient","created":"2025-02-07","cited_by_count":31,"area":"moe"},{"id":"2505.05799","title":"MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design","created":"2025-05-09","cited_by_count":30,"area":"moe"},{"id":"2506.23266","title":"Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging","created":"2025-06-29","cited_by_count":28,"area":"moe"},{"id":"2509.16105","title":"DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning","created":"2025-09-19","cited_by_count":26,"area":"moe"},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"area":"moe"},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21,"area":"moe"},{"id":"2505.19645","title":"MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE","created":"2025-05-26","cited_by_count":19,"area":"moe"},{"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":"2505.21411","title":"Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity","created":"2025-05-27","cited_by_count":18,"area":"moe"},{"id":"2505.04519","title":"Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs","created":"2025-05-07","cited_by_count":12,"area":"moe"},{"id":"2508.12461","title":"Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models","created":"2025-08-17","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":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2510.05245","title":"Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving","created":"2025-10-06","cited_by_count":10,"area":"moe"},{"id":"2505.03531","title":"Faster MoE LLM Inference for Extremely Large Models","created":"2025-05-06","cited_by_count":9,"area":"moe"},{"id":"2505.14136","title":"Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging","created":"2025-05-20","cited_by_count":9,"area":"moe"},{"id":"2508.07785","title":"Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts","created":"2025-08-11","cited_by_count":9,"area":"moe"},{"id":"2504.03871","title":"HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs","created":"2025-04-04","cited_by_count":7,"area":"moe"},{"id":"2504.07964","title":"C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing","created":"2025-04-10","cited_by_count":7,"area":"moe"},{"id":"2506.12417","title":"HarMoEny: Efficient Multi-GPU Inference of MoE Models","created":"2025-06-14","cited_by_count":7,"area":"moe"},{"id":"2501.09410","title":"MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models","created":"2025-01-16","cited_by_count":6,"area":"moe"},{"id":"2510.02324","title":"Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning","created":"2025-09-25","cited_by_count":6,"area":"moe"},{"id":"2506.05767","title":"dots.llm1 Technical Report","created":"2025-06-06","cited_by_count":5,"area":"moe"},{"id":"2510.26730","title":"ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference","created":"2025-10-30","cited_by_count":5,"area":"moe"},{"id":"2505.24205","title":"On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks","created":"2025-05-30","cited_by_count":4,"area":"moe"},{"id":"2507.18671","title":"Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling","created":"2025-07-24","cited_by_count":4,"area":"moe"},{"id":"2510.02613","title":"ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models","created":"2025-10-02","cited_by_count":4,"area":"moe"},{"id":"2511.08968","title":"Bayesian Mixture of Experts For Large Language Models","created":"2025-11-12","cited_by_count":4,"area":"moe"},{"id":"2503.22517","title":"Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities","created":"2025-03-28","cited_by_count":3,"area":"moe"},{"id":"2505.19427","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","created":"2025-05-26","cited_by_count":3,"area":"moe"},{"id":"2504.04444","title":"On the Spatial Structure of Mixture-of-Experts in Transformers","created":"2025-04-06","cited_by_count":2,"area":"moe"},{"id":"2504.15527","title":"Compass-V2 Technical Report","created":"2025-04-22","cited_by_count":2,"area":"moe"},{"id":"2602.17798","title":"Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds","created":"2026-02-19","cited_by_count":2,"area":"moe"},{"id":"2603.03967","title":"UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization","created":"2026-03-04","cited_by_count":2,"area":"moe"},{"id":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"area":"moe"},{"id":"2608.15018","title":"S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices","created":"2026-08-15","cited_by_count":2,"area":"moe"},{"id":"2504.09265","title":"Mixture of Group Experts for Learning Invariant Representations","created":"2025-04-12","cited_by_count":1,"area":"moe"},{"id":"2505.06272","title":"A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning","created":"2025-05-06","cited_by_count":1,"area":"moe"},{"id":"2508.11801","title":"VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models","created":"2025-08-15","cited_by_count":1,"area":"moe"},{"id":"2509.23830","title":"Bayesian Mixture-of-Experts: Towards Making LLMs Know What They Don't Know","created":"2025-09-28","cited_by_count":1,"area":"moe"},{"id":"2601.14792","title":"Robustness of Mixtures of Experts to Feature Noise","created":"2026-01-21","cited_by_count":1,"area":"moe"},{"id":"2602.01468","title":"A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts","created":"2026-02-01","cited_by_count":1,"area":"moe"},{"id":"2603.07006","title":"Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures","created":"2026-03-07","cited_by_count":1,"area":"moe"},{"id":"2604.06291","title":"TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models","created":"2026-04-07","cited_by_count":1,"area":"moe"},{"id":"2605.25565","title":"RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism","created":"2026-05-25","cited_by_count":1,"area":"moe"},{"id":"2510.20111","title":"AsyncHZP: Hierarchical ZeRO Parallelism with Asynchronous Scheduling for Scalable LLM Training","created":"2025-10-23","cited_by_count":0,"area":"moe"},{"id":"2603.13364","title":"FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach","created":"2026-03-09","cited_by_count":0,"area":"moe"},{"id":"2605.26496","title":"Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling","created":"2026-05-26","cited_by_count":0,"area":"moe"},{"id":"2605.31268","title":"Mellum2 Technical Report","created":"2026-05-29","cited_by_count":0,"area":"moe"},{"id":"2608.12419","title":"LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2609.08682","title":"HDA-MoE: Hybrid Parallelism and Dynamic, Adaptive Scheduling for Mixture-of-Experts with 3D Near-Memory Processing","created":"2026-09-08","cited_by_count":0,"area":"moe"},{"id":"2610.04473","title":"InferOpt: Constrained Multi-Objective Search for LLM Inference Configurations","created":"2026-10-03","cited_by_count":0,"area":"moe"}],"next_cursor":null}