Most vision-language-action (VLA) policies decouple manipulation from cognition by bolting an external action mechanism onto a vision-language model (VLM)--either quantizing actions into discrete tokens whose errors bear no stable correspondence to physical displacements, or delegating continuous trajectory generation...
Cheng-Cheng Wang, Wei He, Wen-Hao Li et al.· 0 citations
This work introduces \lifd{} (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene memory that learns scene tokens through multi-view agreement, then completes them from a single RGB view and recurrent memory using rectified flow.
Wen-Bo Li, Yi-Teng Chen, Wen-Hao Li et al.· 0 citations
Dual-Frontier, a learning principle that admits a world-model-guided decision only when its predicted advantage exceeds a certified bound on decision-relevant world-model error; otherwise, evidence is allocated to world-model verification.
Hua-Tai Zhu, Qiang Chen, Zi-Qian Kou et al.· 1 citation
StateTrace is proposed, a novel object-centric framework that endows VideoLLMs with an explicit mechanism for hidden state reasoning in long videos, and builds a reusable spatiotemporal state memory that organizes object trajectories, inter-object relations, and state-transition events into a structured reasoning subst...
Yu Han, Wen-Hao Li, Yi-Chao Cao et al.· 0 citations
Trajectory-Aware Commit Gating (TACG), a training-free gate-level decoder that anchors token identities to the base posterior and uses trajectory-aware signals only to decide whether the current proposal is ready to commit, is proposed.
Chengcheng Wang, Tingzhang Luo, Wenhao Li et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.