{"total":22,"rows":[{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"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":"2609.01343","title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","created":"2026-09-01","cited_by_count":18,"area":"moe"},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"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":"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":"2511.17127","title":"Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design","created":"2025-11-21","cited_by_count":5,"area":"moe"},{"id":"2602.01203","title":"Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse","created":"2026-02-01","cited_by_count":5,"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":"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":"2605.23893","title":"Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models","created":"2026-05-22","cited_by_count":1,"area":"moe"},{"id":"2509.14269","title":"SparseDoctor: Towards Efficient Chat Doctor with Mixture of Experts Enhanced Large Language Models","created":"2025-09-15","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":"2603.15402","title":"A Closer Look into LLMs for Table Understanding","created":"2026-03-16","cited_by_count":0,"area":"moe"},{"id":"2603.24876","title":"OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding","created":"2026-03-25","cited_by_count":0,"area":"moe"},{"id":"2606.24320","title":"ZONOS2 Technical Report","created":"2026-06-23","cited_by_count":0,"area":"moe"},{"id":"2608.09119","title":"Motif 3: Technical Report","created":"2026-08-10","cited_by_count":0,"area":"moe"},{"id":"2608.10605","title":"Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts","created":"2026-08-11","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":"2609.00791","title":"Instella-MoE Technical Report","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2610.18010","title":"Fish Audio Drama 3 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}