arxiv:2306.06236
Xiyang Wu
wuxiyang
·
AI & ML interests
Reinforcement learning, Robotics, LLM
Recent Activity
upvoted
a
paper
29 days ago
Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form
Generation
commented on
a paper
29 days ago
Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form
Generation
upvoted
a
paper
about 1 month ago
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for
Synthetic Videos
Organizations
models
0
None public yet
datasets
0
None public yet