EA-WM is presented, an Event-Aware Generative World Model that effectively closes the loop between kinematic control and visual perception, and introduces event-aware bidirectional fusion blocks that modulate cross-branch attention, capturing object state changes and interaction dynamics.
Qualitative examples show the PhysBrain 1.5 model's ability to produce end-effector trajectories and predict future scenes through spatially aligned RGB, depth, and robot-mask outputs.
DeepCybo Team, Yue Bin, Hai-Peng Cao et al.· 0 citations
It is argued that FBFM offers a new paradigm for fine-grained online correction, bridging open-loop flow generation with closed-loop real-world dynamics.
IntentVLA is introduced, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation and improves rollout stability and outperforms strong VLA baselines.
Shijie Lian, Bin Yu, Xiaopeng Lin et al.· arXiv.org· 6 citations
SIEVE, a structure-aware data selection method for VLA imitation learning that can surpass full-data training while using only 50% of demonstrations and 50% of training steps, suggests that reusable structure, captured through primitives and transitions, is an important signal for efficient VLA imitation learning.
Changti Wu, Bin Yu, Zhaolong Shen et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
