Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
☆272Feb 10, 2026Updated 4 months ago
Alternatives and similar repositories for Pref-GRPO
Users that are interested in Pref-GRPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation☆139Jun 19, 2026Updated last week
- Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex☆789Jun 18, 2026Updated last week
- Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.☆87May 4, 2025Updated last year
- paper collection: alignment of diffusion models☆29Mar 6, 2026Updated 3 months ago
- ☆15Nov 18, 2025Updated 7 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [CVPR 2026] Fine-Grained GRPO for Precise Preference Alignment in Flow Models☆63Jun 1, 2026Updated 3 weeks ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,369May 7, 2026Updated last month
- (ICLR 2026)Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing’☆60Jan 26, 2026Updated 5 months ago
- CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning☆36Aug 28, 2025Updated 10 months ago
- BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models☆47Oct 30, 2025Updated 7 months ago
- [NeurIPS 2025] Official implementation of HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance☆87Sep 18, 2025Updated 9 months ago
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆310Dec 5, 2025Updated 6 months ago
- [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆928Feb 10, 2026Updated 4 months ago
- Official implementation of MagicFace: Training-free Universal-Style Human Image Customized Synthesis.☆66Dec 24, 2024Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆37Jan 21, 2025Updated last year
- Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment [ICCV 2025] - Official implementation☆45Aug 5, 2025Updated 10 months ago
- Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models☆63Jan 3, 2026Updated 5 months ago
- From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning - CVPR 2025☆18Mar 24, 2025Updated last year
- Official codes for the paper "GARDO: Reinforcing Diffusion Models without Reward Hacking"☆59May 3, 2026Updated last month
- [CVPR 2025] Official implementation of ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way☆48Oct 10, 2025Updated 8 months ago
- [ICLR 2026] An official implementation of "STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence"☆43Apr 19, 2026Updated 2 months ago
- [AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆414Mar 26, 2025Updated last year
- An official implementation of Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching☆80Sep 11, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2026] Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆62Jan 26, 2026Updated 5 months ago
- [NeurIPS 2025] Improving Video Generation with Human Feedback☆475Sep 24, 2025Updated 9 months ago
- PICABench: How Far Are We from Physically Realistic Image Editing?☆38Nov 5, 2025Updated 7 months ago
- [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation☆865Mar 19, 2026Updated 3 months ago
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆506Dec 6, 2025Updated 6 months ago
- [ICLR 2026] EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling☆251Mar 20, 2026Updated 3 months ago
- [ICLR 2026] An official implementation of "SIM-CoT: Supervised Implicit Chain-of-Thought"☆207Apr 13, 2026Updated 2 months ago
- An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation☆1,615Oct 16, 2025Updated 8 months ago
- The official repository of our paper "Reinforcing Video Reasoning with Focused Thinking"☆36Jun 12, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Official Implementation of SAGE-GRPO:Manifold-Aware Exploration for Reinforcement Learning in Video Generation☆125Apr 2, 2026Updated 2 months ago
- [ICCV 2025] MM-IFEngine: Towards Multimodal Instruction Following☆122Feb 13, 2026Updated 4 months ago
- [AAAI2026] Implementation Code for Omni-Effects☆175Dec 9, 2025Updated 6 months ago
- Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).☆426Aug 26, 2025Updated 10 months ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆39May 9, 2024Updated 2 years ago
- Official code for paper Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models☆87Apr 23, 2026Updated 2 months ago
- [ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"☆218Updated this week