Starred repositories
34
stars
written in Python
Clear filter
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Fast and memory-efficient exact attention
State-of-the-Art Text Embeddings
[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 transparent bridge between Git and Dropbox - use a Dropbox (shared) folder as a Git remote! 🎁
The official Python client for the Hugging Face Hub.
Papers and Datasets about Point Cloud.
[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"
Physically Based Shading and Deferred Rendering for the Panda3D game engine
PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, ben…
Official GitHub repository for Argoverse dataset
The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"
[CVPR 2025] DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation & [ICLR 2024] DFormer & [NeuriPS 2025] OmniSegmentor
A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题
Neural Scene Flow Prior (NeurIPS 2021 spotlight)
[WACV2025 Oral] SUM: Saliency Unification through Mamba for Visual Attention Modeling
[ECCV 2024] PolyRoom: Room-aware Transformer for Floorplan Reconstruction
[ICLR 2025] You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs
[ACL2024 Findings] Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM