AI 开源项目榜。
[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723
Salesforce open-source LLMs with 8k sequence length.
LUKE -- Language Understanding with Knowledge-based Embeddings
[ECCV 2020] Learning Enriched Features for Real Image Restoration and Enhancement. SOTA results for image denoising, super-resolution, and image enhancement.
Artificial intelligence for MapleStory that uses machine learning and computer vision to navigate challenging in-game environments
Interactive subagents for pi — spawn, orchestrate, and manage sub-agent sessions in cmux terminals
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
Claude Code plugin: automated code review loop with Codex
Poker engine for poker AI development in Python
DRA Driver for NVIDIA GPUs
Collection of reproducible deep learning for compressive sensing
Code for the paper "Generative Adversarial Imitation Learning"
A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Using Keras and Deep Deterministic Policy Gradient to play TORCS
Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling
ComfyUI Node
Dalaran — Apache-2.0, robotics-first visualization and data infrastructure for multimodal time-series. ROS 2 native, reads existing .rrd recordings. A hard fork of Rerun.
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
在vscode插件中结合chatgpt能力，实现智能研发提效
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
The agent skills I actually use to build software with coding agents. The PIV loop, planning, worktrees, and the meta-skills for building your own AI Layer.
[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”
Use Codex from your phone while the real work stays on your computer.
Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020
A concise but complete implementation of CLIP with various experimental improvements from recent papers
Annotate terminal text, review documents and agent replies in Herdr, and send the feedback straight back to the agent.
PyTorch elastic training