Papers

Filtered to dynamics representations · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

17 upvotes · 30 JUL 2026 · Jin Cao, Zian Meng, Kaipeng Zhang

This paper introduces ShadowDancer, a method for teaching video world models to perform any-action control by learning unified dynamics representations from a video and its shadow. Practitioners might care because it can improve action transfer and long-term control in complex environments.

video world modelsany-action controldynamics representationsshadow pairscross-shadow prediction