Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
cs.CV, cs.AI, cs.LG
Submitted: 2025-07-06
Updated: 2026-11-09
Code: https://github.com/shap/shap
Terminology
Sources
- A Comprehensive Survey on Self-Interpretable Neural Networks
- Editing Models with Task Arithmetic
- Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
- Prediction via Shapley Value Regression
- Efficient XAI Techniques: A Taxonomic Survey
- DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
- DataComp: In search of the next generation of multimodal datasets
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs