Pith. sign in

REVIEW 3 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.14705 v1 pith:ET27ZIUY submitted 2024-05-23 cs.CV

Sixian Zhang , Bohan Wang , Junqiang Wu , Yan Li , Tingting Gao , Di Zhang , Zhongyuan Wang This is my paper · ORCID
classification cs.CV
keywords preferencehumanmulti-dimensionaltext-to-imageimageslearnmodelspreferences
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training

    cs.CV 2026-08 conditional novelty 6.0 of 10

    SURE learns sample-adaptive variance in a latent reward model and uses that variance to weight dense post-training feedback, improving image and video diffusion alignment in reported experiments.

  2. Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Z-Reward trains a 27B reasoning teacher VLM on score distributions via GDSO and distills it via RISD into a 9B student, reaching 89.6% and 88.6% human preference accuracy with 41.3% optimization gain over SFT baseline.

  3. ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ImageReFL combines base-model early diffusion steps with a real-image-based fine-tuning objective to improve the quality-diversity trade-off in reward-aligned text-to-image generation.

Pith tools