{"total":16,"rows":[{"id":"2307.05956","title":"Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition","created":"2023-07-12","cited_by_count":26,"area":"moe"},{"id":"2410.10626","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","created":"2024-10-14","cited_by_count":17,"area":"moe"},{"id":"2310.07188","title":"Adaptive Gating in Mixture-of-Experts based Language Models","created":"2023-10-11","cited_by_count":16,"area":"moe"},{"id":"2309.16178","title":"LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASR","created":"2023-09-28","cited_by_count":6,"area":"moe"},{"id":"2406.18021","title":"SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR","created":"2024-06-26","cited_by_count":6,"area":"moe"},{"id":"2411.19402","title":"On the Role of Discrete Representation in Sparse Mixture of Experts","created":"2024-11-28","cited_by_count":4,"area":"moe"},{"id":"2502.00281","title":"Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective","created":"2025-02-01","cited_by_count":4,"area":"moe"},{"id":"2507.05724","title":"Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition","created":"2025-07-08","cited_by_count":4,"area":"moe"},{"id":"2305.13993","title":"Condensing Multilingual Knowledge with Lightweight Language-Specific Modules","created":"2023-05-23","cited_by_count":3,"area":"moe"},{"id":"2406.15883","title":"SimSMoE: Solving Representational Collapse via Similarity Measure","created":"2024-06-22","cited_by_count":3,"area":"moe"},{"id":"2407.18581","title":"Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","created":"2024-07-26","cited_by_count":2,"area":"moe"},{"id":"2501.12602","title":"BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR","created":"2025-01-22","cited_by_count":2,"area":"moe"},{"id":"2412.17507","title":"UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition","created":"2024-12-23","cited_by_count":1,"area":"moe"},{"id":"2505.22072","title":"On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition","created":"2025-05-28","cited_by_count":0,"area":"moe"},{"id":"2601.20300","title":"MiLorE-SSL: Scaling Multilingual Capabilities in Self-Supervised Models without Forgetting","created":"2026-01-28","cited_by_count":0,"area":"moe"},{"id":"2607.24030","title":"MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition","created":"2026-07-27","cited_by_count":0,"area":"moe"}],"next_cursor":null}