Stars
Processing deep-learning datasets (i.e. coco, pascal voc, cityscapes, pascal context)
Development kit for MIT Scene Parsing Benchmark
[CVPR-2022] Official implementations of CIRKD: Cross-Image Relational Knowledge Distillation for Semantic Segmentation and implementations on Cityscapes, ADE20K, COCO-Stuff., Pascal VOC and CamVid.
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Model extraction attacks on Machine-Learning-as-a-Service platforms.
The code of paper: Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing (CVPR 2024))
ImageBind One Embedding Space to Bind Them All
openvla / openvla
Forked from TRI-ML/prismatic-vlmsOpenVLA: An open-source vision-language-action model for robotic manipulation.
This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.
Code for ALBEF: a new vision-language pre-training method
[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language
A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
校招技术岗学习路线图与资源推荐.
这个算法的设计目标就是找到DOM中最有可能包含主要内容的"完整片段"，通常这个片段会： 面积足够大（通过lower_bound保证） 结构相对完整（返回完整的父子结构） 内容密度合适（通过面积增量判断）
Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Highlight).
No fortress, purely open ground. OpenManus is Coming.
Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations
Code for the paper "FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents" arXiv:2502.07393
An open source implementation of CLIP.
Paper: CVPR2018, Learning Rich Features for Image Manipulation Detection
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning