This is your work, valued
PhD student at the University of Edinburgh
reid_baseline_with_syncbn. Reimplementation of Bag of Tricks and A Strong Baseline for Deep Person Re-identification
★ 160CL-Visualizing-Feature-Transformation. Improving Contrastive Learning by Visualizing Feature Transformation, ICCV 2021 Oral
★ 90GPC. Python
★ 24Incremental-Generalized-Category-Discovery. Python
★ 15distill_visual_priors. 2nd place solution of ECCV 2020 workshop VIPriors Image Classification Challenge, https://arxiv.org/abs/2008.00261
★ 13TJCS-Course. :bulb: 同济大学计算机科学与技术、信息安全专业课程资源共享仓库。含部分科目介绍、课程教材、报告模板、实验工具等内容。期待更多课程加入……
★ 12tl-YOLOv2. A tensorlayer implementation of YOLOv2: Object Detection for both image and video!
★ 12dual-rank-ncd. Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation. Bingchen Zhao and Kai Han. (NeurIPS 2021)
★ 12dt-tradeoff. [ECCV 2022] Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
★ 6GPT4-V-selenium. Python
★ 4gpu-docker. nvidia-docker image to avoid some troublesome deep learning setting up and incompatible issues
★ 4fpga_final. Verilog
★ 3RushForOffer. 同济大学2021届面经
★ 2MIRB_eval. Python
★ 1awesome-distributed-systems. A curated list to learn about distributed systems
★ 1CycleGAN. A implementation of CycleGAN(https://arxiv.org/abs/1703.10593)
★ 1humanize. From Automated Idea Factory to Realization
★ 1.4kcodex-slides. 🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-first · zero API keys · durable projects.
★ 726airs-bench. AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents
★ 104chinese-independent-developer. 👩🏿💻👨🏾💻👩🏼💻👨🏽💻👩🏻💻中国独立开发者项目列表 -- 分享大家都在做什么
★ 60kjacobian-lens. Companion code for the global workspace interpretability paper
★ 1.6kdynamaxx. Autoresearch for weather dycores
★ 8cfdllmbench. Combining CFDQuery, CFDCodeBench and FoamBench
★ 42PDEBench. PDEBench: An Extensive Benchmark for Scientific Machine Learning
★ 1.2kweatherbenchX. A modular framework for evaluating weather forecasts
★ 235first-steps-toward-automated-ai-research. Research artifacts from Recursive's automated AI research system
★ 187hle. Humanity's Last Exam
★ 1.6kpolyglot-benchmark. Coding problems used in aider's polyglot benchmark
★ 223FML-bench. FML-bench
★ 27awesome-agentic-world-modeling. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
★ 292research-town. [ICML 2025] ResearchTown: Simulator of Human Research Community
★ 207oh-my-opencode. #1 OpenCode Plugin- Battery included. ASYNC SUBAGENTS (YES LIKE CLAUDE CODE) · Curated agents with proper models · Crafted tools like LSP/AST included · Curated MCPs · Claude Code Compatible Layer — Steroids for your OpenCode. The Best LLM Agent Experience is Here.
★ 951inf-thesis-latex-cls. A LaTeX Class for Informatics theses at The University of Edinburgh
★ 35Understand-Anything. Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
★ 77kformal-conjectures. A collection of formalized statements of conjectures in Lean.
★ 1.2kneedle. Foundation model for tiny devices; 14mb, 26m params, 1-6k toks/sec on mobiles, wearables smart home and robots.
★ 3.3kmini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
★ 6.1klearning-beyond-gradients. Heuristic Learning Blog Post
★ 603financial-services. Python
★ 34knew-api. A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥
★ 44kagentic-harness-engineering. Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.
★ 785weco-cli. Production-Grade Autoresearch. Ideal for GPU kernels, ML model development, feature engineering, prompt engineering, and other optimizable code.
★ 82talkie. talkie is a vintage language model from 1930
★ 957OpenGame. OpenGame: Open Agentic Coding for Games
★ 2.8kCubeSandbox. Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
★ 11kAgentPressureBench. Python
★ 6Claude-Code-Game-Studios. Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
★ 24kUnix-Like-Shell. A pure C implementation of a Unix-like system emulating the Bourne Again SHell.
★ 5TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework
★ 95khermes-agent-self-evolution. ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
★ 4.9kMAP-NEO. Python
★ 986shellbench. The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.
★ 133mempalace. The best-benchmarked open-source AI memory system. And it's free.
★ 58kheim. Open-source, self-hosted, AI-native team communication platform — where humans and AI agents are equal citizens
★ 1meta-harness-tbench2-artifact. Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)
★ 1.2kHumanizer-zh. Humanizer 的汉化版本,Claude Code Skills,旨在消除文本中 AI 生成的痕迹。
★ 14kagentapi. HTTP API for Claude Code, Goose, Aider, Gemini, Amp, and Codex
★ 1.5kralph. Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
★ 21kTrellis. The best agent harness.
★ 13k_HypoSpace. Repository for HypoSpace
★ 15Agen. Agen is a minimalist language for agent loops and state machines.
★ 50oh-my-claudecode. Teams-first Multi-agent orchestration for Claude Code
★ 38ksuperpowers. An agentic skills framework & software development methodology that works.
★ 264kalma. ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
★ 250clax. Differentiable Boltzmann solver for cosmology in JAX
★ 56HyperAgents. Self-referential self-improving agents that can optimize for any computable task
★ 2.7kgpupi. Computing 1000000000 digits of pi on GPU, in 5 seconds.
★ 28cc-weixin. TypeScript
★ 157awesome-autoresearch. Curated list of AutoResearch use cases with optimization traces and open source implementations
★ 1kgodogen. Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex
★ 5.2kspec-kit. 💫 Toolkit to help you get started with Spec-Driven Development
★ 125kcrabline. Mock channel server CLI for OpenClaw testing
★ 30artificial-life. A simple (300 lines of code) reproduction of Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction
★ 409MetaClaw. 🦞 Just talk to your agent — it learns and EVOLVES 🧬.
★ 3.5kvllm. A high-throughput and memory-efficient inference and serving engine for LLMs
★ 88kautoresearch. AI agents running research on single-GPU nanochat training automatically
★ 92ksimply. Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
★ 550dream. Python
★ 10popcorn-cli. Rust
★ 173AgiBotWorldChallengeICRA2026-WorldModelBaseline. Baseline Model Repo for World Model Track in AgiBot World Challenge@ICRA 2026
★ 47symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
★ 26knedreamer. Official implementation of the paper "Next Embedding Prediction Makes World Models Stronger"
★ 38ralph-claude-code. Autonomous AI development loop for Claude Code with intelligent exit detection
★ 9.6kcodex. Lightweight coding agent that runs in your terminal
★ 103kslowrun. 100M tokens. Infinite compute. Lowest val loss wins.
★ 518dataclaw. Agent harness to publish your agent chat history as Huggingface datasets.
★ 2.1kzeroclaw. Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀
★ 32kvibetensor. Our first fully AI generated deep learning system
★ 635PageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
★ 35kMonolith. RLM for coding agent
★ 102projdevbench. C++
★ 23optimizationproblems. A collection of optimization problems in mathematics
★ 332NL2RepoBench. Python
★ 145nyar-vm. Rust
★ 10discoverybench. Discovering Data-driven Hypotheses in the Wild
★ 157RD-Agent. Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report
★ 14kopenclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
★ 385kfaster-whisper. Faster Whisper transcription with CTranslate2
★ 25khle-gpqa-error-claims. Python
★ 9hal-harness. Python
★ 311claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 140kHyperscaleES. Jax Codebase for Evolutionary Strategies at the Hyperscale
★ 352eggroll. A Simple High Performance Computing Framework for [Federated] Machine Learning
★ 253metatextgrad. metaTextGrad: Automatically optimizing language model optimizers. Published in NeurIPS 2025.
★ 17ConsistEdit_Code. [SIGGRAPH Asia 2025] Official Implementation of "ConsistEdit: Highly Consistent and Precise Training-free Visual Editing"
★ 73LatentMAS. [ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems
★ 1.1keval-analysis-public. Public repository containing METR's DVC pipeline for eval data analysis
★ 307cifar10-airbench. CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
★ 386gepa. Optimize prompts, code, and more with AI-powered Reflective Optimization
★ 5.9kSEAgent. [ICML-2026] Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"
★ 259VBVR-EvalKit. This is a framework for evaluating reasoning in foundational Video Models.
★ 225AP-MDM. This is the official implementation for paper "On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond".
★ 23curlora. The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.
★ 53GL.inet-MT3000-installation-plug-in. GL.inet-MT3000的科学上网插件安装详解
★ 123RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
★ 2kduo. [ICML 2025] The Diffusion Duality
★ 237Video-As-Prompt. [ICLR 2026] Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"
★ 443anyup. [ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".
★ 573knowledge_flow. Official Implementation of Knowledge Flow Prompting
★ 35blind_watermark. Blind&Invisible Watermark ,图片盲水印,提取水印无须原图!
★ 14kscikit-opt. Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling salesman)
★ 6.6kcifar10-speedrun. CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.
★ 79Awesome-DLMs. The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".
★ 1.2knanochat. The best ChatGPT that $100 can buy.
★ 57kOpenMoE2. The official repo for "OpenMoE 2: Sparse Diffusion Language Models".
★ 58WaveFunctionCollapse. Bitmap & tilemap generation from a single example with the help of ideas from quantum mechanics
★ 25ktextgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
★ 3.7kCookLikeHOC. 🥢像老乡鸡🐔那样做饭。已添加2026年发布的《老乡鸡菜品溯源报告 2.0中新出现的菜品。主要部分于2024年完工,非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》,并做归纳、编辑与整理。CookLikeHOC.
★ 24kopenai-agents-python. A lightweight, powerful framework for multi-agent workflows
★ 28kThinking-Claude. Let your Claude able to think
★ 17kML-Master. The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"
★ 437marconi. Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
★ 64xiaohongshu-mcp. MCP for xiaohongshu.com
★ 15kopen-in-overleaf. Edit latex of any arxiv.org paper directly on overleaf
★ 213academia_mcp. Academia MCP server: Tools for automatic scientific research
★ 90Awesome-Nano-Banana-images. A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development of image generation and unified models(click to website to see our blog)
★ 23kcheckpoint-engine. Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
★ 988Open-dLLM. Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.
★ 644automated-interpretability. Python
★ 1.1kopenevolve. Open-source implementation of AlphaEvolve
★ 6.8kspecter. SPECTER: Document-level Representation Learning using Citation-informed Transformers
★ 587Memento. Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
★ 2.5krtmlib. RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
★ 3IMO25. An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
★ 935EMoE. Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]
★ 39Agent_Foundation_Models. Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.
★ 580gpt-5-coding-examples. GPT-5 coding examples
★ 1.9krendergit. Render any git repo into a single static HTML page for humans or LLMs
★ 2.4kGl-inet-SFT1200-ipks. SFT1200型号路由器自用ipk安装包
★ 68nvm. Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions
★ 94kDatasetResearch. DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery
★ 23BALROG. Benchmarking Agentic LLM and VLM Reasoning On Games
★ 261matrix. Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.
★ 283WeTok. [ICLR2026] WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
★ 71open-swe. An Open-Source Asynchronous Coding Agent
★ 10kjasmine. A simple, performant and scalable JAX-based world modeling codebase.
★ 156gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
★ 20kGenieRedux. A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agent (AutoExplore Agent), and GenieRedux-G - an implementation of Genie with enhancements
★ 77PhysicsLM4. Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality
★ 356GPT-Image-Edit. GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
★ 243nle. The NetHack Learning Environment
★ 137nle. The NetHack Learning Environment
★ 986awesome-open-ended. Awesome Open-ended AI
★ 459maxtext. A simple, performant, and scalable Jax LLM!
★ 2.4kml-flextok. FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
★ 325aideml. AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
★ 1.5ksample-efficient-nanogpt. Train GPT in as Few Tokens as Possible
★ 2DiscreteLatentCode. Official repository for the article Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models (https://arxiv.org/abs/2507.12318)
★ 38autodiscovery-neurips. Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"
★ 197InfoDiffusion. InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models
★ 36oumi. Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
★ 9.4kDeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent
★ 20khnet. H-Net: Hierarchical Network with Dynamic Chunking
★ 869torchprime. torchprime is a reference model implementation for PyTorch on TPU.
★ 48Manifesto-against-the-Plagiarist-Yunhe-Wang. 讨贼王云鹤檄文
★ 1.1kaira-dojo. AIRA-dojo: a framework for developing and evaluating AI research agents
★ 155True-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。
★ 12kfineweb-2. Python
★ 256MIRB. Benchmarking Multi-Image Understanding in Vision and Language Models
★ 11ReID5o_ORBench. [NeurIPS2025] ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
★ 93dowhen. An intuitive and low-overhead instrumentation tool for Python
★ 1.2kllm-speedrunner. The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in language modeling.
★ 145MM_INF. An efficient multi-modal instruction-following data synthesis tool and the official implementation of Oasis https://arxiv.org/abs/2503.08741.
★ 40EvaLearn. EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks.
★ 431QST. Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
★ 49token-opt. Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"
★ 206ReLIFT. Official Repository of "Learning what reinforcement learning can't"
★ 85dgm. Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
★ 2.2kmodded-nanogpt. NanoGPT (124M) in 90 seconds
★ 5.6kLimine. Modern, secure, portable, multiprotocol bootloader and boot manager.
★ 3.5kscipdf_parser. Python PDF parser for scientific publications: content and figures
★ 455Alita.
★ 882MeanFlow. PyTorch implementation of MeanFlow & iMF (one-step generative modeling).
★ 1.2ktcs. Book in preparation: introduction to theoretical computer science
★ 1.1kOpenVision. OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3
★ 489open-thoughts. Fully open data curation for reasoning models
★ 2.3kAIOS. AIOS: AI Agent Operating System
★ 6.2kMemoryLLM. The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM with Scalable Long-Term Memory"
★ 318Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
★ 27kcognitive-behaviors. Python
★ 224tview. Terminal UI library with rich, interactive widgets — written in Golang
★ 14kGRPO-Zero. Implementing DeepSeek R1's GRPO algorithm from scratch
★ 1.9kPocketFlow-Tutorial-Codebase-Knowledge. Pocket Flow: Codebase to Tutorial
★ 13kT-HOneCls. Class prior-free PU Learning for hyperspectral imagery (ICCV 2023)
★ 26vpu. A PyTorch implementation of the Variational approach for PU learning
★ 31MAGI-1. MAGI-1: Autoregressive Video Generation at Scale
★ 3.8kPRIME. Scalable RL solution for advanced reasoning of language models
★ 1.9kKimina-Prover-Preview. Technical report of Kimina-Prover Preview.
★ 375Liquid. (Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators
★ 642Seed-Thinking-v1.5.
★ 811DiffuLLaMA. [ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models
★ 401WISE. [ICML 2026🔥] WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
★ 212Archon. The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
★ 23kVeOmni. VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
★ 2.1kT2I-ImageNet. Code for "How far can we go with ImageNet for Text-to-Image generation?" paper
★ 98Matcha-TTS. [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
★ 1.3k