mlsanityData to 7 Oct 2026

TempViz: On the Evaluation of Temporal Knowledge in Text-to-Image Models

arXiv 2601.14951 ↗First posted 21 Jan 2026cs.CV cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Time alters the visual appearance of entities in our world, like objects, places, and animals. Thus, for accurately generating contextually-relevant images, knowledge and reasoning about time can be crucial (e.g., for generating a landscape in spring vs. in winter). Yet, although substantial work exists on understanding and improving temporal knowledge in natural language processing, research on how temporal phenomena appear and are handled in text-to-image (T2I) models remains scarce. We address this gap with TempViz, the first data set to holistically evaluate temporal knowledge in image generation, consisting of 7.9k prompts and more than 600 reference images. Using TempViz, we study the capabilities of five T2I models across five temporal knowledge categories. Human evaluation shows that temporal competence is generally weak, with no model exceeding 75% accuracy across categories. Towards larger-scale studies, we also examine automated evaluation methods, comparing several established approaches against human judgments. However, none of these approaches provides a reliable assessment of temporal cues - further indicating the pressing need for future research on temporal knowledge in T2I.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 36 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

19 of 36 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  7. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  8. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  9. 2021A Dataset for Answering Time-Sensitive Questionscited by 150
  10. 2024Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluationcited by 123
  11. 2024Large Language Models Can Learn Temporal Reasoningcited by 110
  12. 2023What You See is What You Read? Improving Text-Image Alignment Evaluationcited by 105
7 more
  1. 2024Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoningcited by 83
  2. 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environmentscited by 52
  3. 2024Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratingscited by 44
  4. 2023Measuring Progress in Fine-grained Vision-and-Language Understandingcited by 25
  5. 2023Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuningcited by 18
  6. 2021Probing Language Models for Understanding of Temporal Expressionscited by 16
  7. 2025Around the World in 24 Hours: Probing LLM Knowledge of Time and Placecited by 6

Built on by

Not cited yet.