2 papers
cs.RO2026
Beyond Instance Slots: Semantically Rich World Models for Physical Interaction Planning
Juntao Cheng, Jingkai Wang, Yijun Shen +2
World models for physical interaction are typically trained to predict future observations or latent features; however, a planning-oriented model must answer a fundamentally differ…
cs.RO2026
SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation
Jingkai Wang, Zihan Tang, Gu Zhang +7
Vision-language-action policies rely on large multimodal backbones to jointly perform perception, language conditioning, and action generation at every control step. Much of this c…