Pointing-gesture visual grounding requires connecting hand geometry with the visual identity and extent of a referred object. A central challenge for continuous latent reasoning is how to organize these complementary cues into useful intermediate supervision. We propose Spatial Latent Reasoning (SLR), a framework that...
Ling Li, Jian-Hui Zhong, Wei Liu et al.· 0 citations
Results show that continually revising skill guidance as the agent's capabilities change helps transform external skills into policy capabilities that require no skill inputs at inference.
Ling Li, Qiu-Yu Shen, Zheng Jiang et al.· 0 citations
While standard end-to-end baselines struggle to complete these logically demanding tasks, ACE achieves a 50% success rate in equation formation and a 70% success rate in constraint retrieval, demonstrating that explicit workflow reasoning and mask-mediated control offer a robust, practical route toward adaptable roboti...
Iok Tong Lei, Qianzhi Li, Ying Jie Yap et al.· arXiv.org· 0 citations
XS-VLA is introduced, a lightweight framework that teaches tiny VLA policies "where to look" and "how to move" without increasing deployment-time model cost and shows that explicit spatial grounding and latent action-structure learning can make tiny VLA models effective for robotic manipulation.
Iok Tong Lei, Ying Jie Yap, Wei Huang 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.
