Robots can use historical observations to answer spatiotemporal queries in familiar environments, but the presence of relevant evidence does not imply that existing tools support the operations a task requires. We introduce ReSight, a task-driven self-improving memory system for embodied agents that expands the capabil...
Li-Rong Che, Yang Chen, Yi-Meng Su et al.· 1 citation
Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, but embodied RSI methods either refine the harness around a frozen executor and so cannot add a missing motion, or train the executor on persistent failures without aski...
Pei-Dong Wang, Ying Chang, Zhi-Ming Ma et al.· 4 citations
This work introduces HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness and demonstrates its applicability to both navigation tasks in real-world environments.
Yang Chen, Li-Rong Che, Zhen-Yu Huang et al.· 8 citations· ⚡2
GeoWorldAD is proposed, a geometry world action model that grounds trajectory planning in ego-aligned 3D space and anticipates short-horizon scene evolution with latent future geometry tokens and progressively aggregates multi-scale present geometry and latent future geometry through iterative trajectory refinement.
Song-Yan Zhang, Jin-Yu Tian, Han-Bing Li et al.· arXiv.org· 1 citation
This work introduces VAR-VTON, a VAR-based VTON model that incorporates garment conditioning and structural guidance for efficient latent-space VTON, and proposes STAR-VTON, a Two-Stage AutoRegressive framework that builds upon VAR-VTON by decoupling latent-space structural synthesis from pixel-space detail recovery.
Lu Yang, Xiaonan Hu, Yanan Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
