Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broader behavioral and environmental experience, while learning from them faces a funda...
Chaehyun Kim, Chi-Pin Huang, Jisoo Kim et al.· 0 citations
PhysCaP augments code-as-policy frameworks with a physics-informed exploration layer that enables explicit information-seeking through interaction, and introduces training-free physical property extraction modules that estimate object mass and stiffness from robot proprioception without additional sensors.
TT-VidT leads Jester, Something-Something V2, ARID, and Diving48 fine-tuning simultaneously, improving over the strongest non-TT row by 54% ~ 121%, while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA2.
Shih-Ying Yeh, Daniel Z. Kaplan, Xue-Hai Wang et al.· arXiv.org· 0 citations
In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods rely on offline inference with global temporal sampling, which violates causality and prevents deployment in live surveillance streams. Conversely, general streaming video...
Chia-Hui Chen, Shih-Ying Yeh, Fu-En Yang et al.· 0 citations
This approach reformulates online reconstruction as multi-reference relative pose querying, which achieves state-of-the-art performance across Virtual KITTI, Sintel, TUM-Dynamic, ScanNet, and 7-Scenes and reaches convergence in 8 hours on a single GPU.
Chin-Yang Lin, Yang-Che Sun, Cheng Sun 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.