2026 07 05 rlxf26
Our work Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking has been accepted at ICML 2026 Workshop on Reinforcement Learning from World Feedback. Joint work with Vaidehi Bagaria and Nikshep Grampurohit.
Our work Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking has been accepted at ICML 2026 Workshop on Reinforcement Learning from World Feedback. Joint work with Vaidehi Bagaria and Nikshep Grampurohit.