mlsanityData to 7 Oct 2026

Learning Multi-dimensional Human Preference for Text-to-Image Generation

arXiv 2405.14705 ↗First posted 23 May 2024cs.CVcited by 102

Not on the map. Why?

Cited by 45 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images, they reduce the rich tapestry of human preference to a single overall score. However, the preference results vary when humans evaluate images with different aspects. Therefore, to learn the multi-dimensional human preferences, we propose the Multi-dimensional Preference Score (MPS), the first multi-dimensional preference scoring model for the evaluation of text-to-image models. The MPS introduces the preference condition module upon CLIP model to learn these diverse preferences. It is trained based on our Multi-dimensional Human Preference (MHP) Dataset, which comprises 918,315 human preference choices across four dimensions (i.e., aesthetics, semantic alignment, detail quality and overall assessment) on 607,541 images. The images are generated by a wide range of latest text-to-image models. The MPS outperforms existing scoring methods across 3 datasets in 4 dimensions, enabling it a promising metric for evaluating and improving text-to-image generation.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

19 of 25 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2016Improved Techniques for Training GANscited by 2,938
  12. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
7 more
  1. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  2. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  3. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  4. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 376
  5. 2022CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformerscited by 305
  6. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  7. 2023A Perceptual Quality Assessment Exploration for AIGC Imagescited by 54

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 53; 2026: 33.

102 papers.

Sort:

By area:

  1. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  2. 2025Improving Video Generation with Human Feedbackcited by 267
  3. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 196
  4. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 194
  5. 2024VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generationcited by 148
  6. 2025Seedream 3.0 Technical Reportcited by 146
  7. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 115
  8. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 91
  9. 2024MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?cited by 64
  10. 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generationcited by 64
  11. 2025EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modelingcited by 61
  12. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 59
38 more
  1. 2024Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesiscited by 55
  2. 2024LiFT: Leveraging Human Feedback for Text-to-Video Model Alignmentcited by 51
  3. 2025Calibrated Multi-Preference Optimization for Aligning Diffusion Modelscited by 40
  4. 2025Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesiscited by 39
  5. 2024OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimizationcited by 38
  6. 2025Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimizationcited by 35
  7. 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Modelscited by 35
  8. 2024Scalable Ranked Preference Optimization for Text-to-Image Generationcited by 33
  9. 2025EliGen: Entity-Level Controlled Image Generation with Regional Attentioncited by 32
  10. 2025DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Modelscited by 32
  11. 2025Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preferencecited by 30
  12. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 30
  13. 2024Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLMcited by 22
  14. 2024Rectified Diffusion Guidance for Conditional Generationcited by 18
  15. 2025Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learningcited by 17
  16. 2026PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformerscited by 16
  17. 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferencescited by 13
  18. 2025Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Modelcited by 11
  19. 2025The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generationcited by 11
  20. 2025GeoRemover: Removing Objects and Their Causal Visual Artifactscited by 9
  21. 2025LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spacescited by 8
  22. 2025ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Modelscited by 8
  23. 2025NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Modelscited by 8
  24. 2025Composition and Alignment of Diffusion Models using Constrained Learningcited by 8
  25. 2024Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generationcited by 7
  26. 2025Towards Self-Improvement of Diffusion Models via Group Preference Optimizationcited by 7
  27. 2025I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Modelscited by 7
  28. 2025PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modelingcited by 7
  29. 2024SynFER: Towards Boosting Facial Expression Recognition with Synthetic Datacited by 6
  30. 2025DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?cited by 5
  31. 2025DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learningcited by 5
  32. 2025ContentV: Efficient Training of Video Generation Models with Limited Computecited by 5
  33. 2026FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Spacecited by 5
  34. 2026Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modelingcited by 5
  35. 2024TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Stepscited by 4
  36. 2025Evaluating and Predicting Distorted Human Body Parts for Generated Imagescited by 4
  37. 2025Jailbreaking Safeguarded Text-to-Image Models via Large Language Modelscited by 4
  38. 2025DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Modelscited by 4

50 most cited of 102 All 102 (JSON)