Hao Li

lh152

7 1

·

AI & ML interests

None yet

Recent Activity

liked a dataset about 20 hours ago

RefVideo6M/RefVideo6M

upvoted a paper about 1 month ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

authored a paper about 2 months ago

GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation

View all activity

Organizations

lh152 's papers 6

arxiv:2607.02642

arxiv:2604.08168

arxiv:2603.17240

arxiv:2602.12099

arxiv:2601.04137

arxiv:2509.22642