Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions are physically executed. Existing fault-recovery methods often require task-specific retraining, fault labels, explicit diagnosis, or privileged embodiment information. We...
Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, De-Yuan Qu et al.· 0 citations
A generated video of a task the robot is about to perform is useful guidance only if it depicts the phase the robot is actually in. We show that temporal misalignment can turn a task-consistent generated future into actively harmful guidance. On CALVIN, a five-frame early shift nearly erases the benefit of generated fu...
Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Zhi-Yuan Gao et al.· 0 citations
A knowledge extraction and reasoning module based on a vision-language model that associates object and action descriptions with inferred task conditions, demonstration references, and permissible execution variations is developed, which translates into executable demonstrations that exhibit multimodal behavior through...
Zhi-Yuan Gao, Yan Zhan, Mohammad Khoshnazar et al.· 0 citations
This work proposes FOCAL-VLA, a framework that combines subtask-guided geometry distillation with implicit world modeling to learn representations of current spatial structure and future interaction dynamics, and shows that FOCAL-VLA outperforms baselines on both simulation benchmarks and real-world manipulation tasks.
This work proposes TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE), and constructs a unified four-paradigm dataset with trajectory progress scoring, video-QA answer quality scoring, and their pairwise counterparts.
Yi-Dong Wang, Yan Zhan, Ziteng Feng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
