Stars
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
List of startups doing AI & ML
Pytorch implementation of Self-Refining Video Sampling
Building a Secure and Interoperable Future for AI-Driven Payments.
Specification and documentation for the Universal Commerce Protocol (UCP)
StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart
Official repo for: Epipolar Geometry Improves Video Generation Models
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
A native policy enforcement layer for AI coding agents. Built on OPA/Rego.
[ICLR 2026] SoFlow: Solution Flow Models for One-Step Generative Modeling
Official PyTorch Implementation of "Don't Play Favorites: Minority Guidance for Diffusion Models" (ICLR 2024)
Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"
📷 [CVPR'26] Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!
[CVPR 2026] Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
An open-source toolbox for fast sampling of diffusion models. Official implementations of our works published in ICML, NeurIPS, CVPR, J. Stat. Mech.
Official implementation of Constrained Synthesis with Projected Diffusion Models (NeurIPS 2024)
Official implementation of Training-Free Constrained Generation With Stable Diffusion Models (NeurIPS 2025 Spotlight)
What's in a Prior? Learned Proximal Networks for Inverse Problems
[ICLR'24] Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
[NeurIPS'25] Official implementation of "Emergent Temporal Correspondences from Video Diffusion Models"
[NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO