296 citations
- Hanoi University of Science and TechnologyVN6 papers
- Hong Kong University of Science and TechnologyHK3 papers
- Monash UniversityAU3 papers
- National University of SingaporeSG3 papers
- University of AizuJP3 papers
- University of Illinois Urbana-ChampaignUS3 papers
- University of LuxembourgLU3 papers
- Vietnam National University Ho Chi Minh CityVN3 papers
- Agency for Science, Technology and ResearchSG2 papers
- Can Tho UniversityVN2 papers
- Deakin UniversityAU2 papers
- Fulbright University VietnamVN2 papers
Showing 2023 · cs.LGShow all
2 papers · 2 filters
cs.LG2023★ 10 cited
Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning
Wei Tan, Lan Du, Wray Buntine
The effectiveness of active learning largely depends on the sampling efficiency of the acquisition function. Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the red…
cs.LG2023
HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts
Giang Do, Khiem Le, Quang Pham +7
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the rout…