mlsanityData to 14 Oct 2026

Understanding Dementia Speech Alignment with Diffusion-Based Image Generation

arXiv 2508.09385 ↗First posted 12 Aug 2025cs.LG cs.AIcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Text-to-image models generate highly realistic images based on natural language descriptions and millions of users use them to create and share images online. While it is expected that such models can align input text and generated image in the same latent space little has been done to understand whether this alignment is possible between pathological speech and generated images. In this work, we examine the ability of such models to align dementia-related speech information with the generated images and develop methods to explain this alignment. Surprisingly, we found that dementia detection is possible from generated images alone achieving 75% accuracy on the ADReSS dataset. We then leverage explainability methods to show which parts of the language contribute to the detection.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 14 of its 31 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

14 of 31 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  8. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  9. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  10. 2020Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challengecited by 104
  11. 2020To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detectioncited by 49
  12. 2021Explainable Identification of Dementia from Transcripts using Transformer Networkscited by 19
2 more
  1. 2023Evaluating Picture Description Speech for Dementia Detection using Image-text Alignmentcited by 4
  2. 2024DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speechcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LoRA-Tuned Large Language Models for Dementia Detection via Multi-View Speech-Derived Features
  2. 2025National Institute on Aging PREPARE Challenge: Early Detection of Cognitive Impairment Using Speech -- The SpeechCARE Solution
  3. 2025LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data
  4. 2025NeuroXVocal: Detection and Explanation of Alzheimer's Disease through Non-invasive Analysis of Picture-prompted Speech
  5. 2024Profiling Patient Transcript Using Large Language Model Reasoning Augmentation for Alzheimer's Disease Detection
  6. 2026ADP-DiT: Text-Guided Diffusion Transformer for Brain Image Generation in Alzheimer's Disease Progression
  7. 2026REVEAL: Multimodal Vision-Language Alignment of Retinal Morphometry and Clinical Risks for Incident AD and Dementia Prediction
  8. 2026Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability