Lists (17)
2d generative models
2d GAN & Diffusion & Autoregressive, etc.3d generative networks
3d reconstruction
multi-view to 3d volume & surface3d representations
awesome tutorials
datasets
foundation models
modular implementations
multi-modal LLMs
multi-stage 3D generation
optimization based 3d generation
pretrained estimators
pretrained estimators for depth, normal, etc.texture/material generation
useful tools
vibe coding
video generation models
world models
Stars
ResearchStudio: Our AI co-author, from research problem to final publication.
Online markdown editor with native typora-theme support.
[SIGGRAPH Asia 2026 Journal Track] InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis
VidaForge: Building a Video Foundation Model Pretraining Data Pipeline from Scratch in an Academic Lab
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
We write your reusable computer vision tools. 💜
Infinite Interactive World Rollout on a Single Desktop GPU
Infinite Worlds with Versatile Interactions
Full-stack open-source interactive long-horizon world model.
Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders
[ECCV 2026] Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
[ECCV 2026] WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
Karpathy's LLM-Wiki vision, fully realized — wiki-centric full-lifecycle AI research platform powered by Claude Code
Laas: 3D world built by Claude Fable 5 to test its capabilities using three.js
high-performance inference and serving library for interactive autoregressive video and world models
JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
Python tool for converting files and office documents to Markdown.
TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.
ViGeo: Towards Consistent Video Geometry Estimation
Official code for paper "InstantSfM: Towards GPU-Native SfM for the Deep Learning Era"
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed …