🎓 Automatically Update Some Fields Papers Daily using Github Actions (Update Every 12th hours)

Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization

Repository for Gabriella Norman's master thesis project: A segmentation network with a class-agnostic loss function to train on incomplete data

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss (CVPR 2023)

🏠 PyTorch implementation of our ICCV2021 paper: StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation

Implementation for "Plug-and-Play: Improve Depth Prediction via Sparse Data Propagation"

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

[ArXiv 2024] WildAvatar: Web-scale In-the-wild Video Dataset for 3D Avatar Creation

RWKV v5,v6 LoRA Trainer on Cuda and Rocm Platform. RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN an…

Official pytorch implementation for "LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models"

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022

[ACM MM'2024]"DiffMM: Multi-Modal Diffusion Model for Recommendation"

[TPAMI 2024] Probabilistic Contrastive Learning for Long-Tailed Visual Recognition

Code for 'Keep Your Eye on the Best: Contrastive Regression Transformer for Skill Assessment in Robotic Surgery', published in IEEE Robotics and Automation Letters (RA-L), February, 2023.

Official implementation of "Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery", ICRA 2023.

A curated list of world models for autonomous driving. Keep updated.

This is my study notes for my PhD in AI, NLP, IR, and more.

my notebook !

Implementations of some important or interesting algos.

《深度学习》因封面为一簇花丛又称“花书”，是由深度学习领域老、中、青三代结合而成的经典之作，被业界尊称为“AI圣经”。其中Yoshua Bengio为深度学习的三驾马车之一，Ian Goodfellow因发明了GAN而闻名，最后Aaron Courville为青年研究者。花书从应用数学基础开始，围绕着神经网络拓展开来，因此相较于《机器学习》全面介绍不同类型的算法，花书可以看作为神经网络章节的…

周志华《机器学习》又称西瓜书是一本较为全面的书籍，书中详细介绍了机器学习领域不同类型的算法(例如：监督学习、无监督学习、半监督学习、强化学习、集成降维、特征选择等)，记录了本人在学习过程中的理解思路与扩展知识点，希望对新人阅读西瓜书有所帮助！

some real example of machine learn algorithm

概率图模型学习

高斯混合模型，分离前景和背景图片

The EM Algorithm for Gaussian Mixtures （高斯混合模型的EM算法实现）

my machine learning notes