An embodied brain, or System 2, must turn an abstract goal into actions while discovering relevant scene conditions and checking whether executed skills achieved their intended effects. Open-loop evaluations cannot test observations shaped by an agent's decisions, while some closed-loop evaluations provide limited evid...
Long-WAM is presented, a model-system framework for scaling the context of causal world-action models under real-time control constraints, and finds that access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively (AR).
Wei Huang, Bo-Han Zhang, Chen-Zhi Liu et al.· 1 citation
D$^2$-VLA is presented, which combines dual memory and dual-frequency control at the KV-cache interface of a pretrained VLA, which uses block-wise causal KV caching to encode observations incrementally and constructs separate historical KV read views for the VLM and action expert.
Zi-Jian Ye, Chen Wei, Wei Huang et al.· 0 citations
AffordanceWAM is introduced, an affordance-aware generative World Action Model that represents object-centric spatiotemporal affordance through Scalar Affordance and Affordance Heatmap, within the generated future World, and supports affordance as an effective interface for both vision-language-action learning and huma...
The method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation, and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift.
Yi-Cheng Xiao, Wenxun Dai, Xinran Qin et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.