Zhou

xinyu04

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis

upvoted a paper 9 days ago

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

upvoted a paper 9 days ago

Mosaic: Multi-Session Agentic Reinforcement Learning

View all activity

Organizations

xinyu04 's models 1

xinyu04/ppo-LunarLander-v2

Reinforcement Learning • Updated Mar 5, 2025