MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It targets a key limitation of current video world models—restricted or predefined action spaces—by aiming for arbitrary actions and fine-grained control; the project page and arXiv paper make the approach publicly accessible while code release is planned.
Who it is for
- Researchers in video generation and world models
- Computer vision researchers studying action-conditioned dynamics
- AI developers building interactive simulation or media tools
Use cases
- Enabling frame-level user control in interactive video generation
- Learning action representations for world models from videos without manual action labels
- Building video-based simulation environments with arbitrary action inputs
Strengths
- Proposes any-action, frame-level control for interactive video world models
- Introduces a unified dynamics representation learned from a video and its shadow
- Provides an arXiv paper and project website with visual teaser
- States code and model weights are planned for release after internal review
Considerations
- Code and model weights are not yet publicly available
- README does not include benchmark numbers or system-level comparisons
- Adoption currently depends on reading the paper and waiting for the official release
README quick start
ShadowDancer
Teaching Video World Models Any Action from a Video and Its Shadow
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
Jin Cao, Zian Meng, Kaipeng Zhang† († corresponding author)
ShadowDancer gives interactive video world models an any-action, frame-level control.
The code and model weights are being cleaned up and are undergoing internal review before release.🚧
Citation
@misc{cao2026shadow,
title={ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow},
author={Jin Cao and Zian Meng and Kaipeng Zhang},
year={2026},
eprint={2607.28362},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2607.28362},
}
Description
Code release for https://shadowdancer-1.github.io/
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.