Pinned Repositories
Awesome-Image-Inpainting
A curated list of image inpainting and video inpainting papers and resources
CapsNet-Pytorch
Pytorch version of Hinton's Capsule Theory paper: Dynamic Routing Between Capsules
CDLA
CDLA: A Chinese document layout analysis (CDLA) dataset
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
Gasyori100knock
画像処理100本ノックして画像処理を画像処理して画像処理するためのもの For Japanese, English and Chinese
Global-and-Local-Attention-Based-Free-Form-Image-Inpainting
Official implementation of "Global and local attention-based free-form image inpainting"
Hyper-Table-OCR
A carefully-designed OCR pipeline for universal boarded table recognition and reconstruction.
Learning-to-See-in-the-Dark
Learning to See in the Dark. CVPR 2018
ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
MPRNet
Official repository for "Multi-Stage Progressive Image Restoration" (CVPR 2021). SOTA results for image deblurring, deraining, and denoising.
world2025's Repositories
world2025/CAG
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
world2025/CogAgent
An open-sourced end-to-end VLM-based GUI Agent
world2025/colpali
The code used to train and run inference with the ColPali architecture.
world2025/DeepEP
DeepEP: an efficient expert-parallel communication library
world2025/DeepSeek-R1
world2025/DeepSeek-V3
world2025/DRR
world2025/DRT-o1
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
world2025/FinGLM2
智谱AI 2024年金融行业大模型挑战赛仓库
world2025/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
world2025/FlashMLA
world2025/HippoRAG
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.
world2025/IMAGDressing
[AAAI 2025]👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing. It enables customizable human image generation with flexible garment, pose, and scene control, ensuring high fidelity and garment consistency for virtual dressing.
world2025/Logic-RL
world2025/olmocr
Toolkit for linearizing PDFs for LLM datasets/training
world2025/open-r1
Fully open reproduction of DeepSeek-R1
world2025/open-r1-text2graph
Open replication of DeepSeek R1 for text-to-graph extraction.
world2025/OpenManus
No fortress, purely open ground. OpenManus is Coming.
world2025/PIKE-RAG
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
world2025/PPTAgent
world2025/R1-V
Witness the aha moment of VLM with less than $3.
world2025/RAGEN
RAGEN is the first open-source reproduction of DeepSeek-R1 for training agentic models via reinforcement learning.
world2025/Search-o1
Search-o1: Agentic Search-Enhanced Large Reasoning Models
world2025/shap
A game theoretic approach to explain the output of any machine learning model.
world2025/simpleRL-reason
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
world2025/TIGER
TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
world2025/TinyZero
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
world2025/unlock-deepseek
DeepSeek 系列工作解读、扩展和复现。
world2025/unsloth
Finetune Llama 3.3, DeepSeek-R1, Reasoning, Phi-4 & Gemma 2 LLMs 2x faster with 70% less memory
world2025/Wan2.1
Wan: Open and Advanced Large-Scale Video Generative Models