{"total":24,"rows":[{"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":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39,"area":"moe"},{"id":"2601.18699","title":"Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2026-01-26","cited_by_count":14,"area":"moe"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"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":"2606.26560","title":"Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention","created":"2026-06-25","cited_by_count":5,"area":"moe"},{"id":"2506.18145","title":"Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection","created":"2025-06-22","cited_by_count":4,"area":"moe"},{"id":"2507.06363","title":"Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation","created":"2025-07-08","cited_by_count":3,"area":"moe"},{"id":"2412.11834","title":"Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture","created":"2024-12-16","cited_by_count":1,"area":"moe"},{"id":"2601.01260","title":"MambaFormer: Token-Level Guided Routing Mixture-of-Experts for Accurate and Efficient Clinical Assistance","created":"2026-01-03","cited_by_count":1,"area":"moe"},{"id":"2605.17598","title":"Mixture of Experts for Low-Resource LLMs","created":"2026-05-17","cited_by_count":1,"area":"moe"},{"id":"2607.09424","title":"A Sovereign, Open-Source Foundation Model for German and English","created":"2026-07-10","cited_by_count":1,"area":"moe"},{"id":"2607.20145","title":"SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD","created":"2026-07-22","cited_by_count":1,"area":"moe"},{"id":"2510.26182","title":"MossNet: Mixture of State-Space Experts is a Multi-Head Attention","created":"2025-10-30","cited_by_count":0,"area":"moe"},{"id":"2512.22741","title":"Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis","created":"2025-12-28","cited_by_count":0,"area":"moe"},{"id":"2603.06938","title":"Swimba: Switch Mamba Model Scales State Space Models","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2604.03342","title":"Mixture-of-Experts in Remote Sensing: A Survey","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2608.01284","title":"Training nGPT","created":"2026-08-02","cited_by_count":0,"area":"moe"},{"id":"2608.17744","title":"Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See","created":"2026-08-18","cited_by_count":0,"area":"moe"},{"id":"2608.22613","title":"NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference","created":"2026-08-23","cited_by_count":0,"area":"moe"},{"id":"2608.28511","title":"Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration","created":"2026-08-28","cited_by_count":0,"area":"moe"},{"id":"2609.39137","title":"ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.05484","title":"Universal Test-Time Training","created":"2026-10-04","cited_by_count":0,"area":"moe"}],"next_cursor":null}