Do Domain-specific Experts exist in MoE-based LLMs?

Giang Do

Giang Do Hung Le 0002 Truyen Tran 0001 Do Domain-specific Experts exist in MoE-based LLMs? 2026 April abs/2604.05267 CoRR https://doi.org/10.48550/arXiv.2604.05267 db/journals/corr/corr2604.html#abs-2604-05267 streams/journals/corr

Giang Do Kha Pham Hung Le 0002 Truyen Tran 0001 On the Role of Discrete Representation in Sparse Mixture of Experts. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=GTWKmojpI7 db/journals/tmlr/tmlr2025.html#DoPLT25 streams/journals/tmlr

Giang Do Hung Le 0002 Truyen Tran 0001 SimSMoE: Toward Efficient Training Mixture of Experts via Solving Representational Collapse. 2012-2025 2025 NAACL (Findings) https://doi.org/10.18653/v1/2025.findings-naacl.107 https://aclanthology.org/2025.findings-naacl.107/ conf/naacl/2025f db/conf/naacl/naacl2025f.html#DoLT25 streams/conf/naacl

Giang Do Hung Le 0002 Truyen Tran 0001 Sparse Mixture of Experts as Unified Competitive Learning. 2025 March abs/2503.22996 CoRR https://doi.org/10.48550/arXiv.2503.22996 db/journals/corr/corr2503.html#abs-2503-22996 streams/journals/corr

Giang Do Hung Le 0002 Truyen Tran 0001 S2MoE: Robust Sparse Mixture of Experts via Stochastic Learning. 2025 March abs/2503.23007 CoRR https://doi.org/10.48550/arXiv.2503.23007 db/journals/corr/corr2503.html#abs-2503-23007 streams/journals/corr

Quang Pham Giang Do Huy Nguyen TrungTin Nguyen Chenghao Liu Mina Sartipi Binh T. Nguyen 0001 Savitha Ramasamy Xiaoli Li 0001 Steven C. H. Hoi Nhat Ho CompeteSMoE - Effective Training of Sparse Mixture of Experts via Competition. 2024 abs/2402.02526 CoRR https://doi.org/10.48550/arXiv.2402.02526 db/journals/corr/corr2402.html#abs-2402-02526

Giang Do Hung Le 0002 Truyen Tran 0001 SimSMoE: Solving Representational Collapse via Similarity Measure. 2024 abs/2406.15883 CoRR https://doi.org/10.48550/arXiv.2406.15883 db/journals/corr/corr2406.html#abs-2406-15883

Giang Do Kha Pham Hung Le 0002 Truyen Tran 0001 On the effectiveness of discrete representations in sparse mixture of experts. 2024 abs/2411.19402 CoRR https://doi.org/10.48550/arXiv.2411.19402 db/journals/corr/corr2411.html#abs-2411-19402 streams/journals/corr

Sarita Schoenebeck Amna Batool Giang Do Sylvia Darling Gabriel Grill Daricia Wilkinson Mehtab Khan Kentaro Toyama Louise Ashwell Online Harassment in Majority Contexts: Examining Harms and Remedies across Countries. 485:1-485:16 2023 CHI https://doi.org/10.1145/3544548.3581020 https://www.wikidata.org/entity/Q130868236 conf/chi/2023 db/conf/chi/chi2023.html#SchoenebeckBDDG23

Sarita Schoenebeck Amna Batool Giang Do Sylvia Darling Gabriel Grill Daricia Wilkinson Mehtab Khan Kentaro Toyama Louise Ashwell Online Harassment in Majority Contexts: Examining Harms and Remedies across Countries. 2023 abs/2301.11715 CoRR https://doi.org/10.48550/arXiv.2301.11715 db/journals/corr/corr2301.html#abs-2301-11715

Giang Do Khiem Le Quang Pham TrungTin Nguyen Thanh-Nam Doan Bint T. Nguyen Chenghao Liu Savitha Ramasamy Xiaoli Li 0001 Steven C. H. Hoi HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts. 2023 abs/2312.07035 CoRR https://doi.org/10.48550/arXiv.2312.07035 db/journals/corr/corr2312.html#abs-2312-07035

Louise Ashwell Amna Batool Sylvia Darling Thanh-Nam Doan Gabriel Grill Nhat Ho Steven C. H. Hoi Mehtab Khan Hung Le 0002 Khiem Le Xiaoli Li 0001 Chenghao Liu Binh T. Nguyen 0001 Bint T. Nguyen Huy Nguyen TrungTin Nguyen Kha Pham Quang Pham Savitha Ramasamy Mina Sartipi Sarita Yardi SchoenebeckSarita Schoenebeck Kentaro Toyama Truyen Tran 0001 Daricia Wilkinson