World Action Models (WAMs) extend Vision-Language-Action (VLA) models by incorporating future visual dynamics into action generation. However, existing WAMs often utilize imagined futures with limited adaptation to evolving execution progress, potentially introducing distracting or unreliable predictive cues. This limi...
Yi-Jie Zhu, Zi-Tong Yu, Wei Li et al.· 0 citations
MarKey is a training-free framework that formulates keyframe selection as subset-aware greedy optimization and consistently outperforms existing methods on six benchmarks spanning holistic video understanding, human-centric video understanding, and open-ended video understanding.
Hongchang Shi, Jin-Peng Hu, Ao Wang et al.· 1 citation
The proposed DyCAC framework outperforms existing baselines, exhibiting enhanced social intelligence and broad adaptability across varied multicultural contexts, and is superior on interactive social and cultural benchmarks.
Chongyuan Dai, Ya-Ling Shen, Shen-Geng Tang et al.· 0 citations
This work proposes GMoT, a Gated Motion-Aware Tokenization module that explicitly distills sparse kinematic evidence into a compact sequence prior to temporal modeling, and introduces Body-Region Grounding (BRG) Recall as an anatomical-grounding proxy conditioned on correct predictions.
Taorui Wang, Wei Xia, Hui Ma 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.
