arxiv:2606.09030
Jang
Hyeongwon
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL upvoted a paper 3 days ago
Self-Distilling Future Video Representations for World Action Models upvoted a paper 12 days ago
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache QuantizationOrganizations
None yet
