BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
☆40Oct 30, 2025Updated 4 months ago
Alternatives and similar repositories for BranchGRPO
Users that are interested in BranchGRPO are comparing it to the libraries listed below
Sorting:
- ☆13Jan 22, 2025Updated last year
- Codebase for paper ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools☆29Nov 3, 2025Updated 4 months ago
- The official repository of our paper "Reinforcing Video Reasoning with Focused Thinking"☆35Jun 12, 2025Updated 8 months ago
- [CVPR 2026🔥] Enhancing Spatial Understanding in Image Generation via Reward Modeling☆51Mar 2, 2026Updated last week
- ☆54May 6, 2025Updated 10 months ago
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"☆30Jan 10, 2026Updated last month
- Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning☆241Feb 10, 2026Updated 3 weeks ago
- Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment [ICCV 2025] - Official implementation☆42Aug 5, 2025Updated 7 months ago
- Code of ViewFusion☆54Jul 4, 2024Updated last year
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆62Apr 27, 2025Updated 10 months ago
- Official codes for the paper "GARDO: Reinforcing Diffusion Models without Reward Hacking"☆56Feb 2, 2026Updated last month
- ☆46Aug 15, 2025Updated 6 months ago
- ☆35Nov 6, 2025Updated 4 months ago
- Official repository for TikTok-DeepFake (TT-DF)☆13Feb 17, 2025Updated last year
- [AAAI'2025] Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting☆35Jan 4, 2026Updated 2 months ago
- [ICLR26] GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning☆104Jan 27, 2026Updated last month
- Implementation of followinf estimation algorithms in python: Kalman Filter, Extended Kalman Filter, Unscented Kalman Filter, Cubature Kal…☆11Dec 2, 2023Updated 2 years ago
- MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning [NeurIPS 2025 Poster]☆23Dec 10, 2025Updated 3 months ago
- [TPAMI2025] BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors☆14Apr 23, 2025Updated 10 months ago
- Tools for using the Kinect One (Kinect v2) in ROS☆10Nov 19, 2020Updated 5 years ago
- ☆12Feb 23, 2022Updated 4 years ago
- Repository containing the scripts regarding analyses in Zufferey & Tavernari et al.☆10Feb 22, 2021Updated 5 years ago
- 同济大学数据挖掘课程期末作业：股票走势预测☆10Jan 11, 2021Updated 5 years ago
- Implementation of FaceBaker: Baking Character Facial Rigs with Machine Learning☆11Jun 28, 2020Updated 5 years ago
- ☆16Mar 17, 2025Updated 11 months ago
- Official implementation for “SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World Domain”☆21Dec 11, 2025Updated 2 months ago
- ☆12Oct 17, 2024Updated last year
- The official code of "Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling"☆47Feb 26, 2026Updated last week
- [NeurIPS 2025] E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization☆35Nov 3, 2025Updated 4 months ago
- MLP version of SuperGaussians.☆16Dec 29, 2024Updated last year
- Video packaging platform - this will build a Docker with a web API that will let you upload, encrypt and serve videos as MPEG DASH files☆11Sep 6, 2020Updated 5 years ago
- ☆13Apr 21, 2025Updated 10 months ago
- JoVA: Unified Multimodal Learning for Joint Video-Audio Generation☆30Dec 22, 2025Updated 2 months ago
- ☆24Feb 2, 2026Updated last month
- A python implementation of PSNR that takes the Human visual system into account.☆13Jul 6, 2023Updated 2 years ago
- 同济大学简历模版，做了一点点本地化修改 (generated from fky2015/resume-ng)☆14Dec 3, 2023Updated 2 years ago
- The proposal of this work involves a simulation of an ant colony swarm that was applied to a problem of search and rescue of objects of i…☆12Aug 5, 2023Updated 2 years ago
- GDPnet: "Geometry-guided Dense Perspective Network for Speech-Driven Facial Animation." (TVCG 2021)☆11Nov 21, 2021Updated 4 years ago
- Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization(ACM MM2024)☆18Mar 31, 2025Updated 11 months ago