Cover Image

Language Models Can Explain Visual Features via Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ferrando, Javier, Lopez-Cuena, Enrique, Martin-Torres, Pablo Agustin, Hinjos, Daniel, Arias-Duart, Anna, Garcia-Gasulla, Dario
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Present and Future Generalization of Synthetic Image Detectors
by: Bernabeu-Perez, Pablo, et al.
Published: (2024)

Automatic Evaluation of Healthcare LLMs Beyond Question-Answering
by: Arias-Duart, Anna, et al.
Published: (2025)

The Aloe Family Recipe for Open and Specialized Healthcare LLMs
by: Garcia-Gasulla, Dario, et al.
Published: (2025)

Efficient Safety Retrofitting Against Jailbreaking for LLMs
by: Garcia-Gasulla, Dario, et al.
Published: (2025)

Aloe: A Family of Fine-tuned Open Healthcare LLMs
by: Gururajan, Ashwin Kumar, et al.
Published: (2024)

TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
by: Taghanaki, Saeid Asgari, et al.
Published: (2023)

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
by: Gan, Woody Haosheng, et al.
Published: (2025)

Model-Guided Microstimulation Steers Primate Visual Behavior
by: Mehrer, Johannes, et al.
Published: (2025)

Data Augmentation with Diffusion Models for Colon Polyp Localization on the Low Data Regime: How much real data is enough?
by: Tormos, Adrian, et al.
Published: (2024)

Beyond Intermediate States: Explaining Visual Redundancy through Language
by: Yang, Dingchen, et al.
Published: (2025)

Counterfactual Visual Explanation via Causally-Guided Adversarial Steering
by: Qiao, Yiran, et al.
Published: (2025)

Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations
by: Wang, Chao, et al.
Published: (2025)

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
by: Li, Qiming, et al.
Published: (2026)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
by: Yang, Jiaxi, et al.
Published: (2026)

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
by: Li, Zhuowei, et al.
Published: (2025)

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
by: Balakrishnan, Ravikumar, et al.
Published: (2025)

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
by: Yoon, Hee Suk, et al.
Published: (2026)

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
by: Phute, Mansi, et al.
Published: (2025)

Parallel Backpropagation for Shared-Feature Visualization
by: Lappe, Alexander, et al.
Published: (2024)

Automated Interpretability and Feature Discovery in Language Models with Agents
by: Marin-Llobet, Arnau, et al.
Published: (2026)

Explaining Human Comparisons using Alignment-Importance Heatmaps
by: Truong, Nhut, et al.
Published: (2024)

Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval
by: Bayarri-Planas, Jordi, et al.
Published: (2024)

Can Biases in ImageNet Models Explain Generalization?
by: Gavrikov, Paul, et al.
Published: (2024)

MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale
by: Gai, Xiaotang, et al.
Published: (2024)

VLS: Steering Pretrained Robot Policies via Vision-Language Models
by: Liu, Shuo, et al.
Published: (2026)

Towards Visually Explaining Statistical Tests with Applications in Biomedical Imaging
by: Javanbakhat, Masoumeh, et al.
Published: (2026)

EmoSEM: Segment and Explain Emotion Stimuli in Visual Art
by: Zhang, Jing, et al.
Published: (2025)

Color in Visual-Language Models: CLIP deficiencies
by: Arias, Guillem, et al.
Published: (2025)

CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments
by: Bhagwatkar, Rishika, et al.
Published: (2025)

On Explaining Visual Captioning with Hybrid Markov Logic Networks
by: Shah, Monika, et al.
Published: (2025)

Explainable Pathomics Feature Visualization via Correlation-aware Conditional Feature Editing
by: Yang, Yuechen, et al.
Published: (2026)

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models
by: Zhu, Xingyu, et al.
Published: (2026)

MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
by: Pham, Trong-Thang, et al.
Published: (2026)

Towards Explaining Hypercomplex Neural Networks
by: Lopez, Eleonora, et al.
Published: (2024)

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
by: Liu, Zeyu, et al.
Published: (2026)

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
by: Bi, Jinhe, et al.
Published: (2024)

Explaining How Visual, Textual and Multimodal Encoders Share Concepts
by: Cornet, Clément, et al.
Published: (2025)

Token Activation Map to Visually Explain Multimodal LLMs
by: Li, Yi, et al.
Published: (2025)

MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering
by: Zhou, Yuan, et al.
Published: (2026)

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
by: Huang, Zhuo, et al.
Published: (2023)