Scaling expert demonstrations alone does not enable generalist robot policies to improve from deployment. Real-world rollouts contain successes, suboptimal behavior, and failures: imitating every recorded action can reinforce poor behavior, while filtering out failures discards evidence of physical interactions and their consequences. We introduce LoopWAM, a closed-loop world-action model that learns directly from this full quality spectrum, using rollouts from both itself and other deployed policies. Source-dependent noise sampling unifies behavior learning and action-conditioned world modeling, while quality steering and quality-weighted supervision retain full video supervision across qualities and regulate action imitation. Video and action tokens interact throughout parallel denoising, allowing learned consequences to inform action generation directly. On RoboChallenge Table30-V2, three deployment-and-training rounds raise success from 23.67% to 43.33%, a 19.7-percentage-point gain, with a final score of 56.80. LoopWAM also achieves 94.5% average success on RoboTwin 2.0 and 49.5% overall success on RoboCasa365 without additional embodied pretraining, obtaining the best overall results among the compared methods across all three benchmarks. On challenging shirt folding task, two rounds of deployment-driven improvement after single-task post-training raise success from 13.20% to 55.56%. These results demonstrate closed-loop improvement from mixed-quality experience under both multi-task learning and single-task post-training. Project page: https://loop-wam.github.io/
SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation
University of Toronto(多伦多大学);Vector Institute(向量研究所);NVIDIA(英伟达);Physical Intelligence;Stanford University(斯坦福大学);UC Berkeley(加州大学伯克利分校);Allen Institute for AI(艾伦人工智能研究所)
Effective Tuning Strategies for Generalist Robot Manipulation Policies
University of Adelaide(阿德莱德大学);Commonwealth Scientific and Industrial Research Organisation (CSIRO)(联邦科学与工业研究组织(CSIRO));Shanghai Jiao Tong University(上海交通大学);TikTok
PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
University of Washington(华盛顿大学);Princeton University(普林斯顿大学);University of California, Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学);Toyota Research Institute(丰田研究中心);University of Southern California(南加州大学);Cornell University(康奈尔大学)
Motoniq.ai;Stanford University(斯坦福大学);Istituto Italiano di Tecnologia(意大利技术研究院);ETH Zurich(苏黎世联邦理工学院);Technical University of Darmstadt(德累斯顿技术大学);UCL Centre for AI(伦敦大学学院人工智能中心)