Wanwei He's picture

2 3 9

Wanwei He

Ancient

·

AI & ML interests

Dialog System

Recent Activity

commented on a paper 5 days ago

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

upvoted a paper 5 days ago

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

liked a dataset 27 days ago

llm-blender/Unified-Feedback

View all activity

Organizations

upvoted a paper 5 days ago

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

Paper • 2509.02522 • Published 5 days ago • 23

upvoted a paper 3 months ago

CLaSp: In-Context Layer Skip for Self-Speculative Decoding

Paper • 2505.24196 • Published May 30 • 13

upvoted a collection 7 months ago

Deepseek Papers

Deepseek papers collection • 24 items • Updated 7 days ago • 269