Attention of a Kiss: Generative Video Attention Maps as Explainable and Creative Material
cs.AI, cs.MM
Submitted: 2025-08-30
Updated: 2026-11-14
Terminology
Sources
- Quantifying Attention Flow in Transformers
- Network Bending: Expressive Manipulation of Deep Generative Models
- XAIxArts Manifesto: Explainable AI for the Arts
- Transformer Interpretability Beyond Attention Visualization
- What Does BERT Look At? An Analysis of BERT's Attention
- ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
- Video Diffusion Models
- Understanding Attention Mechanism in Video Diffusion Models
- Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
- What the DAAM: Interpreting Stable Diffusion Using Cross Attention
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- Wan: Open and Advanced Large-Scale Video Generative Models
- Analysis of Attention in Video Diffusion Transformers
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents