Stars
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
The official implementation of the paper "A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts (CVPR 2025)".
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …
A high-throughput and memory-efficient inference and serving engine for LLMs
[NeurIPS 2025 Spotlight] A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone.
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend 🪁
A unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies
Degradation Oriented and Regularized Network for Real-World Depth Super-Resolution (CVPR 2025 Oral)
Official repo for CVPR 2025 paper AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning
LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning
(CVPR2022) Reflash Dropout in Image Super-Resolution
Code for "Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution"
Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with Sparse Transformers"
The implementation of Deformable Spatial Attention in PyTorch.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
The full dataset behind paperswithcode.com
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
结合LightRAG 知识库的知识图谱智能体平台。LangChain v1 + Vue + FastAPI。集成主流大模型、LightRAG、MinerU、PP-Structure、Neo4j 、联网检索、工具调用。
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
A GAN-based method for remote sensing image super-resolution