ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models Paper β’ 2601.11404 β’ Published Jan 16 β’ 26
SOP: A Scalable Online Post-Training System for Vision-Language-Action Models Paper β’ 2601.03044 β’ Published Jan 6 β’ 28
Act2Goal: From World Model To General Goal-conditioned Policy Paper β’ 2512.23541 β’ Published Dec 29, 2025 β’ 23
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation Paper β’ 2508.05635 β’ Published Aug 7, 2025 β’ 73
EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models Paper β’ 2505.09694 β’ Published May 14, 2025 β’ 20
Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning Paper β’ 2503.11646 β’ Published Mar 14, 2025 β’ 34
EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation Paper β’ 2501.01895 β’ Published Jan 3, 2025 β’ 55