Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a fundamental mismatch: driving actions require precise 3D geometric cues, while visual-language understanding and reasoning are largely conducted in a 2D semantic space. In th...
Xing-Tai Gui, Yu-Cheng Zhou, Dong-Qian Guo et al.· 0 citations
BehaviorWorldGen is introduced, a framework that closes the loop between action models and world simulators through controllable behavior-aware structured world generation through controllable behavior-aware structured world generation.
Jia-Qi Wang, Zhuo Zhang, Hai-Ning Guan et al.· 0 citations
Modern driving action models are increasingly improved in a self-improvement loop, where a learned world simulator imagines future observations and the resulting data is fed back to refine the action model. However, the bottleneck of this loop lies in the simulators'inability to generate behaviorally plausible response...
Jiaqi Wang, Zhuo Zhang, Hai-Ning Guan et al.· 0 citations
WA-JEPA is presented, a V-JEPA-native world-action model designed for autonomous driving planning that employs hybrid future-masked pre-training and recast future prediction as conditional flow matching over latent futures, which substantially improves the model's ability to generate plausible future latents for downst...
Xin-Lin Wang, Yu Xiang, Yuheng Zhou 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.
