[AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
☆379Mar 26, 2025Updated 11 months ago
Alternatives and similar repositories for VisionReward
Users that are interested in VisionReward are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] Improving Video Generation with Human Feedback☆428Sep 24, 2025Updated 5 months ago
- Official Implementation of VideoDPO☆160Jun 1, 2025Updated 8 months ago
- [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation☆1,639Oct 29, 2025Updated 4 months ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆661Nov 10, 2025Updated 3 months ago
- Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex☆706Feb 10, 2026Updated 2 weeks ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆646May 24, 2024Updated last year
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,007Nov 4, 2025Updated 3 months ago
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆268Dec 5, 2025Updated 2 months ago
- ☆578Dec 21, 2024Updated last year
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆264Apr 7, 2025Updated 10 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆307Mar 12, 2025Updated 11 months ago
- [ACM Computing Surveys] The collection of awesome papers on alignment of diffusion models.☆403Feb 6, 2026Updated 3 weeks ago
- An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation☆1,529Oct 16, 2025Updated 4 months ago
- official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]☆113Dec 4, 2025Updated 2 months ago
- [CVPR2024 Highlight] VBench - We Evaluate Video Generation☆1,485Updated this week
- Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.☆85May 4, 2025Updated 9 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆153Jun 25, 2024Updated last year
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆454Dec 6, 2025Updated 2 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆242Apr 6, 2024Updated last year
- [ICLR 2025] Autoregressive Video Generation without Vector Quantization☆627Oct 29, 2025Updated 4 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆426Mar 3, 2025Updated 11 months ago
- ☆199Jul 12, 2024Updated last year
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆40May 9, 2024Updated last year
- [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation☆855May 23, 2025Updated 9 months ago
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,936Aug 15, 2024Updated last year
- A unified inference and post-training framework for accelerated video generation.☆3,093Updated this week
- [IEEE TPAMI] Code for the paper "Aligning Few-Step Diffusion Models with Dense Reward Difference Learning"☆19Feb 8, 2026Updated 2 weeks ago
- [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆653Feb 10, 2026Updated 2 weeks ago
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,546Nov 10, 2025Updated 3 months ago
- Repo for "Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content"☆40Jun 9, 2025Updated 8 months ago
- [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.☆1,875Jan 8, 2026Updated last month
- Scalable and memory-optimized training of diffusion models☆1,338Jun 4, 2025Updated 8 months ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆312Nov 1, 2024Updated last year
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆1,230Mar 5, 2025Updated 11 months ago
- ☆54May 6, 2025Updated 9 months ago
- [ICLR 2025, AAAI 2026] official implementation of "Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generati…☆34Jan 26, 2026Updated last month
- Q-Insight is open-sourced at https://github.com/bytedance/Q-Insight. This repository will not receive further updates.☆142May 30, 2025Updated 9 months ago
- Official code for VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control☆191Dec 31, 2024Updated last year
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,553Mar 16, 2025Updated 11 months ago