Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
Paper • 2504.15275 • Published • 2
Jie Cheng
jinachris
AI & ML interests
Reinforcement learning, LLM
Recent Activity
liked a dataset 5 days ago
stepfun-ai/Step-3.5-Flash-SFT liked a model 11 days ago
cerebras/Step-3.5-Flash-REAP-121B-A11B liked a Space 18 days ago
stepfun-ai/Step-3.5-FlashOrganizations
None yet
authored 2
papers 10 months ago