7T MRI synthesization from 3T acquisitions

[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation

本项目设计了一个基于 RAG 与大模型技术的医疗问答系统，利用 DiseaseKG 数据集与 Neo4j 构 建知识图谱，结合 BERT 的命名实体识别和 34b 大模型的意图识别，通过精确的知识检索和问答生成， 提升系统在医疗咨询中的性能，解决大模型在医疗领域应用的可靠性问题。

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Official code for the paper "EAGLE: An Edge-Aware Gradient Localization Enhanced Loss for CT Image Reconstruction".

"RAG-Anything: All-in-One RAG Framework"

Official code for the paper "Filter2Noise: Interpretable Self-Supervised Single-Image Denoising for Low-Dose CT with Attention-Guided Bilateral Filtering"

An AI Hedge Fund Team

Official implementation of BLIP3o-Series

CogView4, CogView3-Plus and CogView3(ECCV 2024)

PyWavelets - Wavelet Transforms in Python

The state-of-the-art image restoration model without nonlinear activation functions.

"Denoising Diffusion Models for Plug-and-Play Image Restoration", Yuanzhi Zhu, Kai Zhang, Jingyun Liang, Jiezhang Cao, Bihan Wen, Radu Timofte, Luc Van Gool.

DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising

Official implementation of Cold-Diffusion for different transformations in pytorch.

Accepted by New Trends in Image Restoration and Enhancement workshop (NTIRE), in conjunction with CVPR 2024.

YOLOE: Real-Time Seeing Anything [ICCV 2025]

[JAMA] "Complete AI-Enabled Echocardiography Interpretation with Multitask Deep Learning" by Gregory Holste, Evangelos K. Oikonomou, Márton Tokodi, Attila Kovács, Zhangyang Wang, & Rohan Khera

Cache-Augmented Generation: A Simple, Efficient Alternative to RAG

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

OpenMMLab Pose Estimation Toolbox and Benchmark.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.