Pre-training

AI & ML interests

None defined yet.

Recent Activity

JW17  authored a paper 28 days ago

AlphaPO -- Reward shape matters for LLM alignment

JW17  authored a paper 28 days ago

Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning

JW17  authored a paper 2 months ago

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

View all activity

Team members 2