This is your work, valued
maua-stylegan2. This is the repo for my experiments with StyleGAN2. There are many like it, but this one is mine. Contains code for the paper Audio-reactive Latent Interpolations with StyleGAN.
★ 179OptimalTextures. An implementation of "Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport"
★ 48maua-style. Neural style transfer
★ 21maua. Generative Art with Machine Learning
★ 9imfuse. Wavelet-based and guided filtering image fusion algorithms
★ 8self-supervised-audio-reactive. Code for my masters thesis "Self-supervised Audio-reactive Music Video Synthesis"
★ 6mmss. Multi-Media Similarity Search
★ 6ml-art-colabs. A list of Machine Learning Art Colabs
★ 3art-DCGAN. Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.
★ 3fedrecsys. Python
★ 2lookahead_minimax. Implementation for the LookaheadMinimax Optimizer.
★ 2stylegan2-ada-pytorch. StyleGAN2-ADA - Official PyTorch implementation
★ 2maua-ddsp. Experiments with ddsp
★ 2trustchain-superapp. Kotlin implementation of Trustchain and IPv8 with rich networking: multihoming of local Bluetooth+4G, decentral social networking, UDP hole punching, etc.
★ 2itunes-music-library-tracks. Creates an stream of tracks from an iTunes Library XML file
★ 2diffwave. DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
★ 2patchmatch-triton. Attempting to implement parallel PatchMatch in Triton
★ 1ALAE. [CVPR2020] Adversarial Latent Autoencoders
★ 1Text-To-Video-Finetuning. Finetune ModelScope's Text To Video model using Diffusers 🧨
★ 1ControlNet3D. Python
★ 1magenta-demos. Demonstrations of Magenta Models
★ 1DenoisingDiffusionGAN. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804
★ 1XM. PyTorch Code for Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
★ 76online-kl-shampoo-release. Python
★ 27TorchLeet. Leetcode for Pytorch
★ 2.4kOptMem. Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
★ 1.1kbatch-2. TeX
★ 17Emerging-Optimizers. Python
★ 248nope. Node-Oriented Procedural Engine
★ 42speedrun-dlm. Python
★ 12Latent-MoE. Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch. A single-file, dependency-light layer you can drop in place of a standard MoE FFN.
★ 16flash-msa. Python
★ 25graphpfn. (ICML 2026) GraphPFN: A Prior-Data Fitted Graph Foundation Model
★ 44TTD. Python
★ 1vpo. Vector Policy Optimization
★ 13git-absorb. git commit --fixup, but automatic
★ 5.7kComfyUI-MagoNodes. Mago Studio Nodes for ComfyUI
★ 6FlashDecoder. Official FlashDecoder Github
★ 18pyg-lib. Low-Level Graph Neural Network Operators for PyG
★ 237defending-code-reference-harness. Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
★ 6.9kremat. torch_remat fine-grained activation checkpointing API
★ 15ideogram4. Ideogram 4: Open image model at the forefront of design
★ 2.6kwall-attention-release. Attention variant with per-channel multiplicative decay
★ 48madmom-modern. Modernized fork of madmom audio analysis library. Works with Python 3.11+ and NumPy 2.x. Neural network-based beat and downbeat detection.
★ 6DEMON. DEMON: Diffusion Engine for Musical Orchestrated Noise
★ 285tokenisation_lp. Python
★ 15dash-attention. DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
★ 22DiT-bending. Supplementary material for Surfacing Control.
★ 6JiT. PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
★ 2.5kmar. PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
★ 1.9kRTM_latent_refinement. Python
★ 22streaming. Code for the paper Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
★ 66flux_matching. Generative Modeling with Flux Matching
★ 66TurboSOAP. SOAP but its really fast
★ 3BitstreamDiffusion. Python
★ 16aurora-release. Aurora optimizer release
★ 151raven. Python
★ 78terratorch. A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
★ 836FD-Loss. Python
★ 549pyrytiles. Python
★ 2cdc-fm. A flow matching model that uses data-driven geometric noise to improve the quality-generalisation tradeoff and to reduce memorisation.
★ 19synthpop. Generating Synthetic Versions of Sensitive Microdata for Statistical Disclosure Control
★ 56LangFlow. The first continuous diffusion language model that rivals discrete counterparts on standard language modeling benchmarks like LM1B and OpenWebText.
★ 86audio-flamingo. PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
★ 1.2ksymbolic-transformer. A next-token predictor using hierarchical label pattern matching instead of float weights, trained by a Claude agent
★ 4the-art-of-debugging. The Art of Debugging Open Book
★ 1.7kaudioic. Estimating musical surprisal/information content in Audio
★ 34Procedural-Modeling-Using-Graph-Grammars. Procedural Modeling Using Graph Grammars
★ 29porymap. Map editor for pokeemerald, pokefirered, and pokeruby
★ 632paper2code. Agent skill to turn any arxiv paper into a working implementation
★ 1.5kpytorch_geometric. Graph Neural Network Library for PyTorch
★ 24kVCC. Compile agent conversations!
★ 393gdds. Code for the paper: "Generalized Discrete Diffusion from Snapshots"
★ 14AutoGaze. AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
★ 297transformer-vm. Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.
★ 215UNITE-tokenization-generation. Single-stage End-to-End Training for Tokenization and Generation
★ 117nucleus-shell. A flexible, extensible desktop shell built with QML, C++, and JavaScript
★ 742ponita. Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.
★ 93ponita-torch. Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.
★ 9MemRoPE. [ECCV 2026] Official implementation of "MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens"
★ 46le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
★ 4.2kfinite-difference-flow-optimization. FDFO: Finite Difference Flow Optimization
★ 115WhatDreamsCost-ComfyUI. LTX Director and a variety of other custom ComfyUI nodes and workflows
★ 1.9kovermind. PyTorch load 模型加速
★ 30browsh. A fully-modern text-based browser, rendering to TTY and browsers
★ 19kdrifting. Python
★ 485ads_model_kernel_library. High-performance GPU kernels for Ads and Recsys model training, independently implemented and optimized for real-world workloads and model-specific input characteristics.
★ 34sinkhorn_drift. Generative Modeling by Drifting through the Gradient Flow of Sinkhorn Divergence
★ 26graphzero. graphzero: High performance C++ backed python library for graphs
★ 71Attention-Residuals.
★ 3.4kflash-kmeans. Fast and memory-efficient exact kmeans
★ 704locality-in-diffusion-models. Official implementation of the paper Locality in Image Diffusion Models Emerges from Data Statistics
★ 47matrixizer-cifar10. Orthogonalizing all layers for Muon optimizer via psgd's matrixizer
★ 2nCPU. nCPU: model-native and tensor-optimized CPU research runtimes with organized workloads, tools, and docs
★ 656flashoptim. Python
★ 258stat_rethinking_2026. Statistical Rethinking Course 2026
★ 816sphere-encoder. PyTorch Implementation of Image Generation with a Sphere Encoder
★ 44comfyui-mcmc. Python
★ 2clifra. Layout-first, fully-planned Clifford algebra engine for PyTorch without runtime overhead.
★ 60CliffordNet-pytorch. Unofficial CAN
★ 21desloppify. Agent harness to make your slop code well-engineered and beautiful.
★ 3ksquared-unitary-pcs. Squared Unitary Probabilistic Circuits
★ 5Y-Shaped-Generative-Flows. Official Pytorch Implementation of "Y-Shaped Generative Flows"
★ 9SP-FM. MixFlow: Mixture-Conditioned Flow Matching for Out-of-Distribution Generalization
★ 13flash-newton-schulz. My attempt to improve the speed of the newton schulz algorithm, starting from the dion implementation.
★ 40PISA. Jupyter Notebook
★ 30avey-b. Code for the Avey-B paper (https://arxiv.org/abs/2602.15814)
★ 32BSNN. Bayesian Sheaf Neural Networks
★ 3Sheaf-NN. A repository benchmarking the SOTA in Sheaf Neural Networks against the SOTA in Graph Neural Networks
★ 1kingdon. A symbolically optimized Geometric Algebra library with PyTorch/NumPy/SymPy/etc. compatibility and ganja.js visualization.
★ 118Side-Step. The most powerful training scripts for ACE-Step 1.5 including a Command Line Interface, a Terminal Wizard and a Graphical User Interface.
★ 148LTX-2. Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
★ 8.5kclaude-desktop-debian. Claude Desktop for Linux
★ 5.3kgaOS. Geometric Algebra for Data Science Open Source
★ 18slop-guard. Slop Scoring to Stop Slop
★ 155reverso. Python
★ 59SemanticBridge. Self-Supervised Semantic Bridge for Unpaired Image-to-Image Translation
★ 24sparse-causal-diffusion. Python
★ 46namo. Jupyter Notebook
★ 13weathr. a terminal weather app with ascii animation
★ 3kpyncd. Python
★ 68HyperMLP. Python
★ 5semicat. Official implementation of Categorical Flow Maps on text.
★ 68pykeen. 🤖 A Python library for learning and evaluating knowledge graph embeddings
★ 2kml-tidbits. Various ML tidbits in Python/PyTorch and C++
★ 88Minimal-Drifting-Models. A minimal implementation of Drifting Models for 2D toy data. Unlike diffusion/flow models that iterate at inference, drifting models evolve the pushforward distribution during training and generate in a single forward pass (1-NFE). The drifting field V governs sample movement: V -> 0 as generated matches data.
★ 73FastGen. NVIDIA FastGen: Fast Generation from Diffusion Models
★ 914companion. Web & Mobile UI for Claude Code & Codex . Launch sessions, stream responses, approve tools. All from your browser / mobile
★ 2.4kmodded-nanotabpfn. speedrunning TFM pretraining
★ 48driftin. Single-step image generation at 306 FPS. Drifting vs Diffusion head-to-head on CIFAR-10.
★ 46Multimodal-RoPEs. Official implement of paper "Revisiting Multimodal Positional Encoding in Vision–Language Models", ICLR 2026
★ 88ranx. ⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍
★ 691bb25. bb25 is a fast, self-contained BM25 + Bayesian calibration implementation with a minimal Python API.
★ 148tangles. This is a python package for data clustering using the tangles algorithmic framework: Clustering with Tangles -- Algorithmic Framework and Theoretical Guarantees (JMLR)
★ 10bartz. Super-fast BART (Bayesian Additive Regression Trees) in Python
★ 96ace-step-skills. Shell
★ 86ACE-Step-1.5. The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
★ 12ktirith. Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.
★ 2.6kmarin. Open-source framework for the research and development of foundation models.
★ 1.2knmoe. MoE training for Me and You and maybe other people
★ 396nw_wrld. nw_wrld is an event-driven sequencer for triggering visuals using web technologies. It enables users to scale up audiovisual compositions for prototyping, demos, exhibitions, and live performances. Users code their own visual modules, then orchestrate them using the project's native UI composer.
★ 2kEBgraph. PostScript
★ 2textarea. A minimalist text editor that lives in URL
★ 2.5kirg. Python
★ 4unify-diffusion. Python
★ 28mdlARC. Goal is to solve sample efficiency by using ARC-AGI as a benchmark
★ 166SpeedrunDiT. SR-DiT Speedrunning ImageNet Diffusion
★ 139gbnet. Gradient Boosting Modules for PyTorch
★ 82cutile-python. cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
★ 2.1kflow-maps. Official codebase for the paper "How to build a consistency model: Learning flow maps via self-distillation" (NeurIPS 2025).
★ 135neural_net_checklist. Python
★ 221flashpack. High-throughput tensor loading for PyTorch
★ 259candi-diffusion. CANDI: Continuous and Discrete Diffusion
★ 28frames-to-video. Python
★ 180bash-screensavers. Turn your idle shell into a visual playground with this collection of Bash screensavers
★ 946Synth-MIA. Jupyter Notebook
★ 5skerch. Sketched linear operations for PyTorch
★ 101curvlinops. PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)
★ 69RND1. RND1: Scaling Diffusion Language Models
★ 186the-markovian-thinker. Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"
★ 349TinyRecursiveModels. Python
★ 6.6kEqM. Python
★ 209SSDD. Official implementation for SSDD Single-Step Diffusion Decoder for Efficient Image Tokenization.
★ 65manifolds. Supporting code for the blog post on modular manifolds.
★ 126ef-vfm. Python
★ 10TSR. [ICML 2026] Official code release for paper "Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models"
★ 54VideoNSA. VideoNSA: Native Sparse Attention Scales Video Understanding
★ 88centralflows. Code for implementing central flows
★ 49OpenTSLM. OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
★ 1.2kllmq. Quantized LLM training in pure CUDA/C++.
★ 252HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
★ 3.2knano-banana-loop. nano-banana-loop
★ 10Wan-Alpha. [CVPR 2026 Highlight] High-Quality Text-to-Video Generation with Alpha Channel
★ 396LongLive. Long Video Gen Infrastructure
★ 2.5kgraphgram. Graph grammar library
★ 52model-synthesis. Model synthesis is a technique for generating 2D and 3D shapes from examples.
★ 212data_efficient_grammar. [ICLR 2022] Data-Efficient Graph Grammar Learning for Molecular Generation
★ 100unfake.py. Pixel-perfect AI art, fast
★ 59expression-generator. Use Retro Diffusion to generate facial expressions for a given input image
★ 20api-examples. RetroDiffusion API examples
★ 143grouped_gemm. PyTorch bindings for CUTLASS grouped GEMM.
★ 192UMoE. Python
★ 24spec-kit. 💫 Toolkit to help you get started with Spec-Driven Development
★ 125knvImageCodec. A nvImageCodec library of GPU- and CPU- accelerated codecs featuring a unified interface
★ 155RamTorch. RAM is all you need
★ 279HFGF. Jupyter Notebook
★ 1libxsmm. Library for specialized dense and sparse matrix operations, and deep learning primitives.
★ 970LEANN. [MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
★ 13kFlexMDM. Jupyter Notebook
★ 55hnet-impl. Trainable H-Net Package
★ 35graphiti. Build Real-Time Knowledge Graphs for AI Agents
★ 29kDaft. High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale
★ 5.7kpueue. :stars: Manage your shell commands.
★ 6.3kflowgrpo. Python
★ 7RecursiveNamespace. Recursive Namespace. An extension of SimpleNamespace
★ 4dinov3. Reference PyTorch implementation and models for DINOv3
★ 11khelion. A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
★ 913grassmann_binary_distribution. Implementation of binary distribution in the Grassmann formalism, including conditional version. Main contributor: Cornelius Schröder (@coschroeder)
★ 5TimeCraft. Official code for TimeCraft: A Time Series Generation Framework for Real-World Applications
★ 1.1kgpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
★ 20kflux-krea-blaze-wan2.2-t2v-rapid-tost. Python
★ 3discreteVAE. Code for our tutorial on Discrete Variational Autoencoders
★ 33Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models
★ 17ksde_matching. Jupyter Notebook
★ 20hnet. H-Net: Hierarchical Network with Dynamic Chunking
★ 869tabicl. TabICLv2: A state-of-the-art tabular foundation model
★ 1.2kpower-attention. Attention Kernels for Symmetric Power Transformers
★ 130DDO. [ICML 2025 Spotlight] Direct Discriminative Optimization: Reinforcing Diffusion/Autoregressive with GAN Discrimination
★ 124torch-cublas-hgemm. PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
★ 78GraphGPS. Recipe for a General, Powerful, Scalable Graph Transformer
★ 874MultipoleAttention. [NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning
★ 24duo. [ICML 2025] The Diffusion Duality
★ 237tabm. (ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling
★ 1.1kSelf-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
★ 3.5kDeltaFM. [ICCV 2025] Official Implementation of Contrastive Flow Matching
★ 184patdb. A snappy + easy + pretty TUI debugger for Python.
★ 71Alternators. This repository contains the implementation of **Alternators**, a novel family of generative models for time-dependent data.
★ 35LaCT. Code release for paper "Test-Time Training Done Right"
★ 500cobalt. best way to save what you love
★ 42kluminal. Inference at the speed of light.
★ 2.9kadjoint_sampling. code for "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching"
★ 140relgt. Relational Graph Transformer
★ 79