Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools. Across successive tasks, however, an agent must also rely on an evolving map and earlier search records, both of which may be incomplete or conflict with new observations. We present...
Xun-Yi Zhao, Jian Zhou, Si-Hao Lin et al.· 0 citations
Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can still violate real-world plausibility, exhibiting malformed object structures, impossible anatomy, physically implausible interactions, or inconsistent spatial relationship...
It is confirmed that, in modulation-conditioned diffusion policies, task adaptation can be routed entirely through the conditioning pathway, leaving a frozen, observation-free backbone that serves as a reusable trajectory prior, and a 5M-parameter MLP backbone matches or exceeds both the 244M U-Net and the transformer...
Jian Zhou, Si-Hao Lin, Shuai Fu et al.· 0 citations
The results show that a general-purpose model can already achieve competitive embodied control without a navigation policy, and term this organization agentic embodied control: the reasoning model directly steers every action, keeping reasoning and control aligned.
This work evaluates three AAS variants across four embodied executors spanning vision-language navigation, embodied question answering, and language-conditioned manipulation, and shows that architecture-level search can produce deployable and directional success-rate gains on embodied tasks, while one apparent high-sco...
Jian Zhou, Sihao Lin, Jin Li et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
