Official repository for FactMM-RAG: Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation [NAACL 2025]

最近重温DETR模型，越发感觉detr模型结构精妙之处，不同于anchor base 与anchor free设计，直接利用100框给出预测结果，使用可学习learn query深度查找，使用二分匹配方式训练模型。为此，我基于detr源码提取解码decode、loss计算等系列模块，并重构、修改、整合一套解码与loss实现的框架，该框架可适用任何backbone特征提取接我框架，实现完整训练…

[ICLR 2025] Official PyTorch implementation of "DECO: Query-Based End-to-End Object Detection with ConvNets"

MICCAI 22 accepted paper “TranSQ: Transformer-based Semantic Query for Medical Report Generation“ for medical report generation

A simple yet powerful agent framework that delivers with open-source models

Solve Visual Understanding with Reinforced VLMs

Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data

[TIP 24] The offical implementation of Efficient Small Object Detection on High-Resolution Images

Official implement of ICLR 2025 "One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning"

[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

This repo provides a working re-implementation of Latent Adversarial Diffusion Distillation by AMD

Hierarchical Reasoning Model Official Release

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

Official repository for the paper "Orientation Matters: Making 3D Generative Models Orientation-Aligned" (NeurIPS 2025)

Demo script showing various image alignment methods.

Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion

Fast Segment Anything

A collaboration friendly studio for NeRFs

Monitor Gaussian Splatting additional real-time viewable and differentiable outputs

Hydra Launcher is an open-source gaming platform created to be the single tool that you need

Code Notes (in Chinese) for 3D Gaussian Splatting

3D高斯论文，持续更新，欢迎交流讨论。

A detailed formulae explanation on gaussian splatting

[TPAMI'25] PanopticNeRF-360 | [3DV'22] Panoptic NeRF (3D-to-2D Label Transfer in Urban Scenes)