{"total":54,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"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":"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":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31,"area":"moe"},{"id":"2503.14487","title":"DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers","created":"2025-03-18","cited_by_count":24,"area":"diffusion"},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2506.14038","title":"Load Balancing Mixture of Experts with Similarity Preserving Routers","created":"2025-06-16","cited_by_count":22,"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":"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":"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":"2601.10639","title":"STEM: Scaling Transformers with Embedding Modules","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2512.05564","title":"ProPhy: Progressive Physical Alignment for Dynamic World Simulation","created":"2025-12-05","cited_by_count":11,"area":null},{"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":"2504.12463","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","created":"2025-04-16","cited_by_count":10,"area":"moe"},{"id":"2601.17111","title":"Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts","created":"2026-01-23","cited_by_count":9,"area":"moe"},{"id":"2604.08541","title":"Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts","created":"2026-04-09","cited_by_count":9,"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":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"id":"2603.17102","title":"Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency","created":"2026-03-17","cited_by_count":6,"area":"moe"},{"id":"2605.15403","title":"$\\phi$-Balancing for Mixture-of-Experts Training","created":"2026-05-14","cited_by_count":5,"area":"moe"},{"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":"2605.06663","title":"EMO: Pretraining Mixture of Experts for Emergent Modularity","created":"2026-05-07","cited_by_count":4,"area":"moe"},{"id":"2505.23926","title":"Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation","created":"2025-05-29","cited_by_count":3,"area":"moe"},{"id":"2602.12556","title":"SD-MoE: Spectral Decomposition for Effective Expert Specialization","created":"2026-02-13","cited_by_count":3,"area":"moe"},{"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":"2605.28042","title":"Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts","created":"2026-05-27","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":"2512.16248","title":"Sigma-MoE-Tiny Technical Report","created":"2025-12-18","cited_by_count":2,"area":"moe"},{"id":"2601.12137","title":"EMoE: Eigenbasis-Guided Routing for Mixture-of-Experts","created":"2026-01-17","cited_by_count":2,"area":"moe"},{"id":"2602.04870","title":"Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism","created":"2026-02-04","cited_by_count":2,"area":"moe"},{"id":"2602.08019","title":"The Rise of Sparse Mixture-of-Experts: A Survey from Algorithmic Foundations to Decentralized Architectures and Vertical Domain Applications","created":"2026-02-08","cited_by_count":2,"area":"moe"},{"id":"2602.19000","title":"MagicAgent: Towards Generalized Agent Planning","created":"2026-02-22","cited_by_count":2,"area":"agents"},{"id":"2511.16947","title":"Fine-grained MoE Load Balancing with Linear Programming","created":"2025-11-21","cited_by_count":1,"area":"moe"},{"id":"2512.09723","title":"Mixture of Lookup Key-Value Experts","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2601.15370","title":"Improving MoE Compute Efficiency by Composing Weight and Data Sparsity","created":"2026-01-21","cited_by_count":1,"area":"moe"},{"id":"2604.07030","title":"MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale","created":"2026-04-08","cited_by_count":1,"area":"moe"},{"id":"2605.27605","title":"Laguna M.1/XS.2 Technical Report","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2504.19592","title":"Neural network task specialization via domain constraining","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2601.05034","title":"How to Set the Batch Size for Large-Scale Pre-training?","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.05537","title":"Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts","created":"2026-01-09","cited_by_count":0,"area":"moe"},{"id":"2604.05130","title":"A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection","created":"2026-04-06","cited_by_count":0,"area":"agents"},{"id":"2605.16690","title":"UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models","created":"2026-05-15","cited_by_count":0,"area":"moe"},{"id":"2605.19945","title":"GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems","created":"2026-05-19","cited_by_count":0,"area":"moe"},{"id":"2605.31463","title":"PithTrain: A Compact and Agent-Native MoE Training System","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.00761","title":"Confidence-Adaptive SwiGLU for Mixture-of-Experts","created":"2026-05-30","cited_by_count":0,"area":"moe"},{"id":"2606.08814","title":"STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning","created":"2026-06-07","cited_by_count":0,"area":"moe"},{"id":"2606.28835","title":"Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning","created":"2026-06-27","cited_by_count":0,"area":"moe"},{"id":"2608.29817","title":"Structure Aware Neural Architecture Search for Mixture of Experts","created":"2026-08-30","cited_by_count":0,"area":"moe"},{"id":"2608.30181","title":"A.X K2 Technical Report","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.08115","title":"Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training","created":"2026-09-08","cited_by_count":0,"area":"moe"},{"id":"2609.22471","title":"Efficient Mixture-of-Experts with Speculative Decoding via Expert Coactivation","created":"2026-09-18","cited_by_count":0,"area":"moe"},{"id":"2609.32398","title":"Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism","created":"2026-09-26","cited_by_count":0,"area":"moe"},{"id":"2610.05744","title":"CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training","created":"2026-10-05","cited_by_count":0,"area":"moe"}],"next_cursor":null}