Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between real-time perception and long-term memory. Retrieving historical information provides a natural remedy, yet historical recall is not uniformly beneficial: unnecessary hi...
Yi Chen, Ming-Ming Yu, Rui-Qi Wang et al.· 0 citations
AtlasVLA is a novel framework that transitions from direct reactive manipulation to proactive reasoning through a persistent world-ego state and decisively outperforms multi-view baselines, yielding absolute success rate improvements of 9.4% on LIBERO-Long and 17.5% in real-world long-horizon tasks.
Guiyu Zhao, Long-Teng Guo, Yang-Hong Mei et al.· 1 citation
This work presents GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments, and introduces one-stage alignment training that jointly optimizes vision-language understanding and multi-embodiment action generation.
GigaBrain Team, An-Gen Ye, Axiang Sun et al.· 7 citations· ⚡1
GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control, and introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts.
GigaWorld Team, Angen Ye, Ang-Yuan Ma et al.· arXiv.org· 3 citations
The Robust-WAM is a general post-training method for video-generation-based WAMs that preserves the VAE-based generative path and adds a lightweight semantic foresight alignment objective on the action stream to retain the large-scale VGM pretraining while grounding actions in appearance-invariant dynamics.
Hao-Dong Yan, Jun-Feng Li, Jun-Jie He et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
