{"total":21,"rows":[{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2311.02684","title":"Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE","created":"2023-11-05","cited_by_count":25,"area":"moe"},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"id":"2406.11256","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","created":"2024-06-17","cited_by_count":19,"area":"moe"},{"id":"2408.12733","title":"SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging","created":"2024-08-22","cited_by_count":16,"area":"moe"},{"id":"2310.15539","title":"SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation","created":"2023-10-24","cited_by_count":9,"area":"moe"},{"id":"2404.15247","title":"XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts","created":"2024-04-23","cited_by_count":7,"area":"moe"},{"id":"2502.12947","title":"Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models","created":"2025-02-18","cited_by_count":6,"area":"moe"},{"id":"2312.14557","title":"Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning","created":"2023-12-22","cited_by_count":3,"area":"moe"},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"id":"2505.21191","title":"Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities","created":"2025-05-27","cited_by_count":2,"area":"moe"},{"id":"2607.20426","title":"Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations","created":"2026-05-08","cited_by_count":2,"area":"moe"},{"id":"2502.02040","title":"M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference","created":"2025-02-04","cited_by_count":1,"area":"moe"},{"id":"2506.13541","title":"Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization","created":"2025-06-16","cited_by_count":1,"area":"moe"},{"id":"2605.11255","title":"HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model","created":"2026-05-11","cited_by_count":1,"area":"moe"},{"id":"2605.28577","title":"Continual Model Routing in Evolving Model Hubs","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2406.02969","title":"Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models","created":"2024-06-05","cited_by_count":0,"area":"moe"},{"id":"2605.08842","title":"XPERT: Expert Knowledge Transfer for Effective Training of Language Models","created":"2026-05-09","cited_by_count":0,"area":"moe"},{"id":"2606.00686","title":"Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing","created":"2026-05-30","cited_by_count":0,"area":"moe"},{"id":"2607.20443","title":"GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus","created":"2026-05-12","cited_by_count":0,"area":"moe"}],"next_cursor":null}