mlsanityData to 14 Oct 2026

Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts

arXiv 2509.05323 ↗First posted 30 Aug 2025cs.AI cs.MMcited by 0

On the map: Diffusion models → Video generation

Abstract (arXiv)

This paper presents an artistic and technical investigation into the attention mechanisms of video diffusion transformers. Inspired by early video artists who manipulated analog video signals to create new visual aesthetics, this study proposes a method for extracting and visualizing cross-attention maps in generative video models. Built on the open-source Wan model, our tool provides an interpretable window into the temporal and spatial behavior of attention in text-to-video generation. Through exploratory probes and an artistic case study, we examine the potential of attention maps as both analytical tools and raw artistic material. This work contributes to the growing field of Explainable AI for the Arts (XAIxArts), inviting artists to reclaim the inner workings of AI as a creative medium.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 9 of its 17 references that are in the map. First posted on arXiv 30 Aug 2025.

Builds on

9 of 17 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Analysis of Attention in Video Diffusion Transformers14 Apr

Other references · 8

  1. 2017Attention Is All You Needcited by 60,361
  2. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  3. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  4. 2020Quantifying Attention Flow in Transformerscited by 775
  5. 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
  6. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  7. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 236
  8. 2025XAIxArts Manifesto: Explainable AI for the Artscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
  2. 2026Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers
  3. 2025Understanding Attention Mechanism in Video Diffusion Models
  4. 2026Attention Dynamics in Diffusion Models: A Visual Analytics Framework for Human-AI Collaboration
  5. 2025The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models
  6. 2025Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
  7. 2023Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation
  8. 2025Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile