AI 开源项目榜。
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Noise2Noise: Learning Image Restoration without Clean Data - Official TensorFlow implementation of the ICML 2018 paper
Implementation of Non-local Block.
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)
Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
World's first general purpose 3D object detection codebse.
Native Multimodal Models are World Learners
Learning Continuous Signed Distance Functions for Shape Representation
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)
YOLOv2 in PyTorch
Neovate Code is a code agent to enhance your development. You can use it to generate code, fix bugs, review code, add tests, and more. You can run it in interactive mode or headless mode.
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
[CVPR 2020] Interpreting the Latent Space of GANs for Semantic Face Editing
[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
AI for GNU Image Manipulation Program
Privacy focused translator app built with MD3
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023 Top-10 Cited 🏆) & (NTIRE 2024 Runner-Up 🏆) & (NTIRE 2025 Winner 🏆) & (NTIRE 2026 Winner 🏆)
A collection of video resources for machine learning
The official Java library for the OpenAI API
PyTorch android examples of usage in applications
A macOS menu bar application that monitors AI coding assistant usage quotas. Keep track of your Claude, Codex, Antigravity ,and Gemini usage at a glance.
Chinese keras documents with more examples, explanations and tips.
State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.
SALMONN family: A suite of advanced multi-modal LLMs
Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.
A reading list on LLM based Synthetic Data Generation 🔥
The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
Training LLMs with QLoRA + FSDP