li sheng's picture

li sheng

bambisheng

·

https://github.com/BambiSheng

AI & ML interests

None yet

Recent Activity

new activity 2 days ago

TsinghuaC3I/ZEDA-Evaluation:Add dataset card and link to paper/code

upvoted a collection 4 days ago

authored a paper 4 days ago

Post-Trained MoE Can Skip Half Experts via Self-Distillation

View all activity

Organizations

authored a paper 4 days ago

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Paper • 2605.18643 • Published 5 days ago • 30

authored a paper about 1 year ago

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published Apr 22, 2025 • 122

authored a paper over 1 year ago

UltraIF: Advancing Instruction Following from the Wild

Paper • 2502.04153 • Published Feb 6, 2025 • 24