This is your work, valued
simple-pytorch-3dgan. A simple and unofficial 3D-GAN implementation using PyTorch [NeurIPS 2016]
★ 92bndm. Blue noise for diffusion models [SIGGRAPH 2024]
★ 53awesome-diffusion-noise. A collection of noise designs for diffusion models [Eurographics Tutorial / SIGGRAPH Course, 2025]
★ 29pytorch_sliced_wasserstein_loss. An unofficial PyTorch implementation of "A Sliced Wasserstein Loss for Neural Texture Synthesis" paper [CVPR 2021].
★ 14pps_gabor_random. Point-Pattern Synthesis using Gabor and Random Filters [EGSR 2022]
★ 4PointFlowRenderer-mitsuba2. Code for rendering the point cloud figures in paper: "PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows"
★ 2pointsets_to_powerspec. A python tool for visualizing point sets and their frequency power spectra.
★ 1reflow-dit. Implementing rectified flow on top of fast-dit for few-step inference.
★ 1facial-expression-recognition. This is the implementation of Feature-Level Joint Learning for Facial Expression Recognition.
★ 1simple-consistency-models. A 200 lines of code unofficial implementation of Consistency Models [Song et al. ICML 2023]
★ 1NonStationaryTextureSyn. Newer version Code for paper "Non-Stationary Texture Synthesis by Adversarial Expansion"
★ 1taichi_smallpt. smallpt in taichi
★ 1Un-0. Un-0: an image generator powered by a simulated system of coupled oscillators, an example of an emerging physical computing substrate.
★ 316PocketFlow. Pocket Flow: 100-line LLM framework. Let Agents build Agents!
★ 11kterrain-diffusion. Procedural generation with diffusion models (SIGGRAPH '26)
★ 1.3kstop-slop. A skill file for removing AI tells from prose
★ 15kGLM-5. GLM-5: From Vibe Coding to Agentic Engineering
★ 6.9kminit2i-torch. Official PyTorch re-implementation of MiniT2I.
★ 294wosx. Grid-Free Monte Carlo Solvers for Physics Simulations Involving Partial Differential Equations
★ 139kimi-code. Kimi Code CLI — The Starting Point for Next-Gen Agents
★ 5.8kMatern-FM. [SIGGRAPH 2026] Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes
★ 31awesome-gpt-image-2. 🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image consistency, and commercial-grade illustration. Free & open source.
★ 9kminWM. A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models
★ 755vggt-omega. [CVPR 2026 Oral] VGGT Omega
★ 3.8kAwesome-LLM-On-Policy-Distillation. A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
★ 485Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
★ 8.6kHRM-Text. HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
★ 1.8knqr. Neural Quadrature Rule and Autoregressive Adaptive Sampling
★ 24QMem. Python
★ 468dna26. 8DNA: 8D Neural Asset Light Transport by Distribution Learning
★ 9FD-Loss. Python
★ 549PixelDiT. [CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation
★ 911MLPZen. C++
★ 77AlayaRenderer. Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds.
★ 709lyra. Project Lyra: Open Generative 3D World Models
★ 2.2kUNITE-tokenization-generation. Single-stage End-to-End Training for Tokenization and Generation
★ 117ERNIE-Image. ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches state-of-the-art performance among open-weight text-to-image models.
★ 494DeCo. [CVPR2026 Highlight] Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”
★ 238jump-restore-light-transport. C++
★ 12ai4animationpy. A Python framework for AI-driven character animation using neural networks.
★ 2.1kQwen3.6. Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.
★ 3.7kanalytic-diffusion-studio. A unified framework for building and studying analytical diffusion models
★ 33smalldiffusion. Simple and readable code for training and sampling from diffusion models
★ 777ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
★ 15kllm-spectral-clipping. Official implementation of the framework of SPECTRA for LLM training. ICML 2026
★ 13arnis. Generate any location from the real world in Minecraft with a high level of detail.
★ 17kautoresearch. AI agents running research on single-GPU nanochat training automatically
★ 93kawesome-openclaw-usecases. A community collection of OpenClaw use cases for making life easier.
★ 32kawesome-phd-advice. Collection of advice for prospective and current PhD students
★ 2.1kQwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
★ 8.2kopenclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
★ 385kslangpy. Making it easier to work with slang in python
★ 153VibePaper. An academic paper recommendation system
★ 12Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
★ 3.5ktaehv. Tiny AutoEncoder for Hunyuan Video (and other video models)
★ 451MAS-Orchestra. MAS-Orchestra: train, inspect, and vibe-code multi-agent systems with RL-learned orchestration and MASBench
★ 22lingbot-world. Advancing Open-source World Models
★ 4.3kfigure-gen. A Python package to effortlessly assemble images in comparison figures. Supports LaTeX, PPTX, and HTML.
★ 151iris.c. Flux 2 image generation model pure C inference
★ 2kHowToVulkan. Minimalist tutorial and code for doing something meaningful with Vulkan in 2026
★ 586minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM!Train a 64M-parameter LLM from scratch in just 2h!
★ 54kIADB. Official implementation of IADB (Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model), published at Siggraph 2023.
★ 174diffusionstudio. Minimalistic and modular library, aimed for fundamental experimentation with generative diffusion models.
★ 2Z-Image. Python
★ 12kchaotic-fractals. Learning Image Fractals Using Chaotic Differentiable Point Splatting - Eurographics 2025
★ 6MimicKit. A lightweight suite of motion imitation methods for training controllers.
★ 2.2kPancap. [NeurIPS 2025] Panoptic Captioning: An Equivalence Bridge for Image and Text
★ 38gilo. Gaussian Integral Linear Operators for Precomputed Graphics
★ 21sam-3d-objects. SAM 3D Objects
★ 7.2kDepth-Anything-3. Depth Anything 3
★ 6kepipolar-dpo. Official repo for: Epipolar Geometry Improves Video Generation Models
★ 96vismatch. Wrapper of 50+ image matching models with a unified interface
★ 900FinDap. Python
★ 26TinyRecursiveModels. Python
★ 6.6knanochat. The best ChatGPT that $100 can buy.
★ 57kPuffin. [ICLR 2026] Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
★ 420openqmc. Quasi-Monte Carlo sampling library for rendering and graphics applications.
★ 95ReSWD. Variance reduction for Sliced Wasserstein Distance using Reservoir Sampling.
★ 10py-meanflow. Pytorch implementation for MeanFlow
★ 363GAMEBoT. [ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games
★ 34GEN3C. [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
★ 1.4kPractiLight. Official Implementation of PractiLight: Practical Light Control Using Foundational Diffusion Models
★ 49neural-shading-s25. Materials for the Neural Shading Course at SIGGRAPH 2025
★ 185neural.slang. Slang
★ 34LeetCUDA. LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.
★ 12kminFM. HTML
★ 175neural-graphics-model-gym. Neural Graphics Model Gym is a Python® toolkit for developing real-time Neural Graphics machine learning models.
★ 68wave_tracer. A wave-optical path tracer
★ 173ode-video. The official repo for [Generative Video Bi-flow, ICCV 2025]
★ 8vvmc. Vector-Valued Monte Carlo Integration Using Ratio Control Variates
★ 45gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
★ 20kTrue-Story-of-Pangu. 诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。
★ 12kvggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
★ 14kgreencloud-paper. Python
★ 18renderformer. Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
★ 967openevolve. Open-source implementation of AlphaEvolve
★ 6.8kMAS-Zero. Designing Multi-Agent Systems with Zero Supervision
★ 120CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
★ 13kimm. Official implementation of Inductive Moment Matching
★ 585Diffusion-Explorer. Interactive visualizations of the geometric intuition behind diffusion models.
★ 1.2kml-hypersim. Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
★ 2knanoVLM. The simplest, fastest repository for training/finetuning small-sized VLMs.
★ 5kDDBM. Python
★ 278vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
★ 25kmerian-quake. A path-tracer for the original Quake game
★ 73BlenderProc. A procedural Blender pipeline for photorealistic training image generation
★ 3.6kdia. A TTS model capable of generating ultra-realistic dialogue in one pass.
★ 19kFramePack. Lets make video diffusion practical!
★ 17kfastms. Real-Time Minimization of the Piecewise Smooth Mumford-Shah Functional
★ 60LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
★ 100kprompt_quill. Python
★ 306AlexNet-Source-Code. This package contains the original 2012 AlexNet code.
★ 3kstable-virtual-camera. Stable Virtual Camera: Generative View Synthesis with Diffusion Models
★ 1.6kCnC_Red_Alert. Command and Conquer: Red Alert
★ 6.7kever_training. Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"
★ 310transformer_latent_diffusion. Text to Image Latent Diffusion using a Transformer core
★ 229taesd. Tiny AutoEncoder for Stable Diffusion (and other image models)
★ 958DeepSeek-R1.
★ 92kRF-Inversion. Rectified Flow Inversion (RF-Inversion) - ICLR 2025
★ 478edm2. EDM2 and Autoguidance -- Official PyTorch implementation
★ 848OneDiffusion. Official implementation of OneDiffusion paper (CVPR 2025)
★ 662flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
★ 4.7kSING. [SIGGRAPH Asia 2024] SING: Stability-Incorporated Neighborhood Graph
★ 8Papers-in-100-Lines-of-Code. Implementation of papers in 100 lines of code.
★ 2.8kNoiseRefine. Official implementation of "A Noise is Worth Diffusion Guidance", code and weights will be available soon.
★ 58DimensionX. [ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
★ 1.3kCosmos-Tokenizer. A suite of image and video neural tokenizers
★ 1.7klatex_paper_writing_tips. Tips for Writing a Research Paper using LaTeX
★ 3.8kTheChosenOne. Unofficial implementation of the paper "The Chosen One: Consistent Characters in Text-to-Image Diffusion Models"
★ 270experimental-consistory. Python
★ 113TokenFormer. [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
★ 593MPMC. Message-Passing Monte Carlo (MPMC)
★ 27ode-appearance. The official repo for [Neural Differential Appearance Equations, TOG (SIGGRAPH Asia 2024)]
★ 21edge-preserving-diffusion. Source code repository for the project "Edge-preserving noise for diffusion models" [Eurographics 2026 / ICLR 2025 DeLTa Workshop].
★ 10Pyramid-Flow. [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
★ 3.2kEdge-Preserving-Nonlinear-Diffusion. Perona-Malik implementation of Nonlinear Diffusion in Python with GUI.
★ 1fcpw. fast distance and ray intersection queries
★ 487vxpg. Real-Time Path Guiding Using Bounding Voxel Sampling
★ 34Awesome-Game-Analysis. a comprehensive collection of video game tech analysis resources
★ 1.2kfast-and-tiny. A basic Monte Carlo raytracer in python
★ 25mcmc-demo. Interactive Markov-chain Monte Carlo Javascript demos
★ 932IC-Light. More relighting!
★ 8.5kOmost. Your image is almost there!
★ 7.6kCameraCtrl. Python
★ 658gpu.cpp. A lightweight library for portable low-level GPU computation using WebGPU.
★ 4kCAMDM. (SIGGRAPH 2024) Official repository for "Taming Diffusion Probabilistic Models for Character Control"
★ 307unet.cu. UNet diffusion model in pure CUDA
★ 661meshgpt-pytorch. Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch
★ 861PALI. Democratization of "PaLI: A Jointly-Scaled Multilingual Language-Image Model"
★ 94ngf. Source code for the SIGGRAPH 2024 paper "Neural Geometry Fields for Meshes"
★ 154easy_pybind. Python
★ 32geodesic_raytracing. C++
★ 134variational-diffusion-models. PyTorch implementation of Variational Diffusion Models.
★ 106ControlNet. Let us control diffusion models!
★ 34kfab3dwire. C++
★ 27ctm. Python
★ 325awesome-flow-matching. A summary of related works about flow matching, stochastic interpolants
★ 692pykan. Kolmogorov Arnold Networks
★ 16kk-diffusion-inverse-problems. [ICML 2024] Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
★ 66dmesh. Official implementation for "DMesh: A Differentiable Representation for General Meshes" (NeurIPS 2024)
★ 328llm.c. LLM training in simple, raw C/CUDA
★ 31kOpenCLAY. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
★ 980Open-Sora. Open-Sora: Democratizing Efficient Video Production for All
★ 29kCWAN. Python
★ 4Multi-view-Datasets. Multi-view datasets for classification or clustering
★ 80STDN. [NeurIPS 2023] Diversifying Spatial-Temporal Perception for Video Domain Generalization
★ 17dust3r. DUSt3R: Geometric 3D Vision Made Easy
★ 7.3kCerule. Cerule - A Tiny Mighty Vision Model
★ 71pytorch_misc. Code snippets created for the PyTorch discussion board
★ 571diso. Differentiable Iso-Surface Extraction Package (DISO)
★ 332bilateral_solver. Python code for the fast bilateral solver
★ 238point-e. Point cloud diffusion for 3D model synthesis
★ 6.9k3DGS.cpp. A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports Windows, Linux, macOS, iOS, and visionOS
★ 776AppearanceFreeActionRecognition. [ECCV 2022] Is Appearance Free Action Recognition Possible?
★ 59VkNRC. Vulkan Implementation of NVIDIA's paper Real-time Neural Radiance Caching for Path Tracing.
★ 41C-Gravity-Simulator. An improvement over my old gravity simulator in Haskell
★ 32Diffusion-Models-Papers-Survey-Taxonomy. Diffusion model papers, survey, and taxonomy
★ 3.4kenigine. Game engine playground.
★ 220XOV-Action. The first work for cross-domain open-vocabulary action recognition with a benchmark
★ 21Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
★ 12kinteractive-viewer. An online test suite for rendering research, based on Disney Research's interactive viewer
★ 44PaintMixing. Python
★ 399webgl-path-tracer. Game and Media Technology MSc at Utrecht University (2020)
★ 28loss-landscapes. Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
★ 359oh-my-cv. An in-browser, local-first Markdown resume builder.
★ 1kfractal. The boundary of neural network trainability is fractal
★ 228Conditional_Diffusion_MNIST. Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
★ 827makeMoE. From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
★ 811SVD_Xtend. Stable Video Diffusion Training Code and Extensions.
★ 731loss-landscape. Code for visualizing the loss landscape of neural nets
★ 3.2kintro_dgm. "Deep Generative Modeling": Introductory Examples
★ 1.3kvectormath. Modified version of Sony's open sourced vector and matrix math library.
★ 315GP100L. Graphics Programming in 100 Lines
★ 126cpp-ml-intro. C++ ML Intro
★ 147libigl-autodiff-example. C++
★ 5flip. A tool for visualizing and communicating the errors in rendered images.
★ 643HybridRenderingEngine. Clustered Forward/Deferred renderer with Physically Based Shading, Image Based Lighting and a whole lot of OpenGL.
★ 1.6kSoftwareRenderer. Software rendering engine with PBR. Built from scratch on C++.
★ 778Vulkan-Forward-Plus-Renderer. Forward+ renderer in Vulkan using Compute Shader. An Upenn CIS565 final project.
★ 698ExcaliburHash. Excalibur Hash is a high-speed hash map and hash set, ideal for performance-critical uses like video games
★ 337tinycompiler. Writing a compiler in a week-end
★ 476New-Grad-2024. 👋 Hey there new grad🎉! We've put together a collection of full-time job openings for SWE, Quant, PM and tech roles in 2024! 🚀
★ 6.2kTamaGo. Computer go engine using Monte-Carlo Tree Search written in Python3.
★ 71hybrid-rendering. A Vulkan sample that demonstrates a Rasterization and Ray Tracing Hybrid Rendering Pipeline.
★ 1kPyTorch-SVGRender. SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.
★ 491mlx-examples. Examples in the MLX framework
★ 8.9kCluster. Clustered shading implementation with bgfx
★ 472diffusion_restart_sampling. Code for NeurIPS 2023 paper "Restart Sampling for Improving Generative Processes"
★ 152bacon. Official respository for "Band-limited Coordinate Networks for Multiscale Scene Representation" | CVPR 2022
★ 179diffusion-posterior-sampling. Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"
★ 6673d-game-shaders-for-beginners. 🎮 A step-by-step guide to implementing SSAO, depth of field, lighting, normal mapping, and more for your 3D game.
★ 20kmlx. MLX: An array framework for Apple silicon
★ 28k