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

A survey for visual generation alignment

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization

[NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".

Open-source unified multimodal model

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

[NeurIPS 2025] Improving Video Generation with Human Feedback

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution

A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability

codes for RFSR: Improving ISR Diffusion Models via Reward Feedback Learning

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

[ECCV2024] Towards Reliable Advertising Image Generation Using Human Feedback

OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…

Official implementations for paper: Anydoor: zero-shot object-level image customization

[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

[CVPR 2023] CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

Fast Approximation of Bilateral Filter Implementation in Pure Python and Comparison with OpenCV and scikit-image Bilateral Implementations

AeDet: Azimuth-invariant Multi-view 3D Object Detection, CVPR2023

AI-Generated Presets for Faithful 4K Color Style Transfer in Real Time [CVPR 2023]

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

[CVPR 2022] Official PyTorch Implementation of "AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement" (https://arxiv.org/abs/2204.13983)

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

Function dependencies resolution and execution

Simple, lightweight, extensible DAG framework for Python with a Kubeflow-like API