3 papers
cs.RO2026
MolmoAct2: Action Reasoning Models for Real-world Deployment
Haoquan Fang, Jiafei Duan, Donovan Clay +26
Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment.…
cs.RO2026
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
Shirui Chen, Cole Harrison, Ying-Chun Lee +6
General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.…
cs.LG2026
A simple connection from loss flatness to compressed neural representations
Shirui Chen, Stefano Recanatesi, Eric Shea-Brown
Despite extensive study, the significance of sharpness -- the trace of the loss Hessian at local minima -- remains unclear. We investigate an alternative perspective: how sharpness…