QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution Paper • 2412.20694 • Published Dec 30, 2024
Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts Paper • 2508.07785 • Published 29 days ago • 25
MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs Paper • 2508.05257 • Published Aug 7 • 13
Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts Paper • 2508.07785 • Published 29 days ago • 25
Value Residual Learning For Alleviating Attention Concentration In Transformers Paper • 2410.17897 • Published Oct 23, 2024 • 9 • 2
Dynamics of Instruction Tuning: Each Ability of Large Language Models Has Its Own Growth Pace Paper • 2310.19651 • Published Oct 30, 2023
Value Residual Learning For Alleviating Attention Concentration In Transformers Paper • 2410.17897 • Published Oct 23, 2024 • 9