Lists (15)
Stars
DeepPrivacy2 - A Toolbox for Realistic Image Anonymization
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
BitDance & UniWeTok: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model.
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
Real-Time Physical Action-Conditioned Video Generation
[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.
Tracking the latest and greatest research papers on video generation.
Interactive World Simulator for Robot Policy Training and Evaluation
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image (CVPR 2026)
🛠「Watt Toolkit」是一个开源跨平台的多功能 Steam 工具箱。
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
A curated list of open-source projects at the intersection of Agent and RL
Collection of forcing related autoregressive video Gen
A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, a…
Elevate your AI research writing, no more tedious polishing ✨
paper collection: alignment of diffusion models
Helios: Real Real-Time Long Video Generation Model
[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
OpenClaw-RL: Train any agent simply by talking
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
Code release of [ICCV2025 Highlight] WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
SPAgent, a foundation agent for understanding, reasoning over, and operating within the physical and spatial world.