World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure e...
Hao-Yi Jiang, Liu Liu, Xin-Jiang Wang et al.· 0 citations
Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions. A key test of such generality is whether policies actually follow language instructions. Yet many manipulation benchmarks leave this ability underdeterm...
Mengao Zhao, Ziang Li, Chaodong Huang et al.· 0 citations
DreamWAM is introduced, which reformulates future prediction as structured world modeling beyond RGB, representing future states through complementary views of appearance, motion, geometry, and semantics, showing that robust world-action learning depends not only on predicting the future, but on representing it in a fo...
Shanglin Yuan, Weiheng Zhao, Xin Shi et al.· 4 citations
Faster-WAM introduces a sparse future-conditioning framework that computes future representations once and selectively reuses them throughout action denoising, and proposes SparseMoT to replace ubiquitous layer-wise fusion with selective video-action interaction at a compact subset of network stages, and Interval KV-Fu...
Weiheng Zhao, Haoyi Jiang, Xin Shi et al.· 10 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
