Home› Projects› MixGRPO
MixGRPO
Python

MixGRPO

[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

by Tencent-Hunyuan · GitHub
1.2k
Stars
50
Forks
2025
Created
2 mo ago
Last commit
diffusion
Category
Python
Language
diffusiongrporeinforcement-learningPython
View on GitHub
In plain words

Run experiments on flow-based models to improve efficiency in reinforcement learning tasks.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
MixGRPO — GitHub preview card
📈 Star history
1 1521 151
2026-07-202026-08-31
📈 Track MixGRPO

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

MixGRPO has 1.2k stars on GitHub. It has been forked 50 times. MixGRPO is written mainly in Python. It has been in active development since 2025. Its main topics are diffusion, grpo, reinforcement-learning.

❓ Frequently asked questions

What is MixGRPO?

[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Is MixGRPO open source?

MixGRPO is an open-source project.

Is MixGRPO free?

Yes. MixGRPO is free and open source — you can use, modify and self-host it.

What language is MixGRPO written in?

MixGRPO is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MixGRPO

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=tencent-hunyuan-mixgrpo)](https://olud.ai/project/tencent-hunyuan-mixgrpo.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
ABC-GRPO
Code For Adaptive-Boundary-Clipping GRPO. arxiv.org/pdf/2601.03895
★ 442 · grpo
sharesgrporeinforcement-learning
Flow-Factory
A unified framework for easy reinforcement learning in Flow-Matching models
★ 629 · diffusion
sharesdiffusionreinforcement-learning
Awesome-RL-for-Video-Generation
A curated list of papers on reinforcement learning for video generation
★ 565 · dpo
sharesgrporeinforcement-learning
OpenThinkIMG
OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.
★ 397 · grpo
sharesgrporeinforcement-learning
VADER
Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models…
★ 315 · alignment
sharesdiffusionreinforcement-learning
MegaDLMs
GPU-optimized framework for training diffusion language models at any scale. The backend of Quo…
★ 344 · diffusion
sharesdiffusion
REPA
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easi…
★ 1.7k · diffusion
sharesdiffusion
StyleKeeper
Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual…
★ 483 · diffusion
sharesdiffusion
PufferLib
Puffing up reinforcement learning
★ 6.2k · reinforcement-learning
sharesreinforcement-learning
sample-factory
High throughput synchronous and asynchronous reinforcement learning
★ 1k · reinforcement-learning
sharesreinforcement-learning

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.