Hung C-Y, Majumder N, Deng H, Renhang L, Ang Y, Herremans D., Wang Z, Poria S..  2026.  Action- and World Model-based Rewards Improve Vision-Language-Action Model Post-Training. NeurIPS workshop: Robot Learning with World Models: Capabilities, Frontiers, and Challenges.

• Google Scholar
• BibTeX