CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Paper
• 2508.03686 • Published
• 39 •
4
Shudong Liu
Sudanl
AI & ML interests
NLP, LLM
Recent Activity
upvoted a paper 18 days ago
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations authored
a paper
24 days ago
Kimi K2.5: Visual Agentic Intelligence upvoted a paper 25 days ago
Kimi K2.5: Visual Agentic Intelligence Organizations
commented a paper 7 months ago
It seems that the train_qa subset only contains multiple-choice questions
#4 opened 9 months ago
by
Sudanl