Vision-language models still struggle to understand 3D spatial relations across views and update spatial judgments as the observer moves. A common approach fuses 3D reconstruction features into visual tokens, but aligning these features with pretrained semantic representations remains challenging under limited spatial...
Han Su, Meng Tian, Tian-Yu Huang et al.· 0 citations
Actions specify what a robot should execute, but do not describe what those commands will achieve. Vision-language-action (VLA) policies nevertheless learn primarily by predicting action chunks from images, language, and state. We introduce Action--Future Coupled Effect Learning (AFCE), which makes a future-grounded ph...
Min Lin, Bo-Kai Zhou, Jian-Qi Lin et al.· 0 citations
Vision-language-action (VLA) policies emphasize semantic understanding, whereas world-action models (WAMs) learn predictive representations of environment dynamics. Systems that expose a policy to both sources often still concentrate action computation on a single expert. We present EWAM, an action-centric unified embo...
Hao Wang, Jia-Jun Wen, Jing-Zhi Liu et al.· 0 citations
VA-Judger is proposed, a chain-of-thought omni-reward model that learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, an...
Yin-Ming Huang, Shu-Yuan Tu, Xi Yan et al.· 6 citations· ⚡1
4D-WAM is presented, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling and effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.
This work proposes AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions, and introduces a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning.
Likui Zhang, Tao Tang, Zhihao Zhan et al.· arXiv.org· 19 citations· ⚡3
This work introduces SUV, a unified end-to-end driving framework that casts future Scene Understanding as Video generation using a pretrained video foundation model, and shows that structured future supervision and direct future-stream access yield higher trajectory planning scores.
Yibo Yuan, Jiacheng Fu, Jiangtong Zhu et al.· 1 citation
Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the"Thinking with Images"(TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, whi...
Xiuwei Chen, Quanlin Chen, Wentao Hu 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.
