CompAdapt extends neural dynamics modeling to composite physical behaviors including coupled motions, multi-stage transitions, and multi-object collisions, overcoming the limitation of prior work to single-type motions.
Text-to-video model that learns composite physics and adapts to new dynamics
CompAdapt models coupled motions, multi-stage transitions, and multi-object collisions from natural language prompts, and generalizes to unseen physical laws via one-shot adaptation.
Chinese Tech
Haoran Qin (Harbin Institute of Technology, China) · Renlong Wu (Harbin Institute of Technology, China) · Tianyu Huang (Harbin Institute of Technology, China) · Yukang Ding (Taobao, Alibaba Group, China) · Hui Li (Harbin Institute of Technology, China) · Wangmeng Zuo (Harbin Institute of Technology, China)
Research Digest··3 min read
Thread:Diffusion Language Models
The authors propose CompAdapt, a diffusion-based text-to-video framework that improves physical consistency by modeling composite motions beyond simple single-type dynamics.
Why this paper
From Alibaba Group and Harbin Institute of Technology
In one line
CompAdapt generates physics-consistent text-to-video with composite motions, prompt-derived physical semantics, and one-shot adaptation to unseen physical laws.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§