We have 6 of 19 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual transition reasoning, and test whether this capability can serve as a shared training primitive, one that different models can learn from diff...
This work proposes DreamAvoid, a critical-phase test-time dreaming framework that enables VLA models to anticipate and avoid failures, and introduces an autonomous boundary learning paradigm to refine the system's understanding of the subtle boundary between success and failure.
Across unseen environments, SPA consistently and substantially improves over vanilla RL: for example, it raises the Sokoban success rate from 25.6% to 59.8% on Qwen2.5-1.5B-Instruct, letting sub-3B models surpass a 20B baseline on these tasks.
WorldAgen is presented, a unified framework that jointly learns world modeling and action prediction while enabling test-time training (TTT) to adapt to new environments, and surpasses existing state-of-the-art models at inference time.
This work introduces HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution in a vision-language model (VLM), and builds HumanCLAW-Bench, a database of 1,218 long-horizon, egocentric find-navigate-interact episodes across 41 indoor scenes.
Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce ManiGuard, a specification-grounded framework for evaluating and improving the safety of foundation-model manipulation, comprising the ManiGuard...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
