EVA: Efficient Reinforcement Learning for End-to-End Video Agent
Paper • 2603.22918 • Published • 42
Xiaowei Yin
AmberYin
AI & ML interests
AI safety
Recent Activity
upvoted a paper 6 days ago
EVA: Efficient Reinforcement Learning for End-to-End Video Agent upvoted a collection about 1 month ago
Rubrics as an Attack Surface (RIPD) upvoted a paper about 1 month ago
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-ConsistencyOrganizations
None yet