Xiyang Wu PRO

wuxiyang

·

AI & ML interests

Reinforcement learning, Robotics, LLM

Recent Activity

upvoted a paper 7 days ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

upvoted a paper 10 days ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

liked a dataset 2 months ago

IntelligenceLab/Cos-Play-Cold-Start

View all activity

Organizations

commented a paper 8 months ago

MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models

Paper • 2511.18373 • Published Nov 23, 2025 • 7 •

commented a paper about 1 year ago

Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation

Paper • 2506.15068 • Published Jun 18, 2025 • 14 •