Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning Paper • 2608.26809 • Published 28 days ago • 7
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs Paper • 2608.20492 • Published Aug 20 • 87
CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing Paper • 2608.17566 • Published Aug 18 • 16