Lists (13)
Stars
Making large AI models cheaper, faster and more accessible
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Official inference repo for FLUX.1 models
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Tongyi Deep Research, the Leading Open-source Deep Research Agent
An open source implementation of CLIP.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…
A collaboration friendly studio for NeRFs
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
Visual localization made easy with hloc
Plenoxels: Radiance Fields without Neural Networks
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
pySLAM is a Python-based Visual SLAM pipeline that supports monocular, stereo, and RGB-D cameras. It offers a wide range of modern local and global features, multiple loop-closing strategies, a vol…
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
A modular high-level library to train embodied AI agents across a variety of tasks and environments.