{"total":29,"rows":[{"id":"2502.14744","title":"HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States","created":"2025-02-20","cited_by_count":33,"area":"mllm"},{"id":"2502.13095","title":"Understanding and Rectifying Safety Perception Distortion in VLMs","created":"2025-02-18","cited_by_count":17,"area":"mllm"},{"id":"2510.21518","title":"Head Pursuit: Probing Attention Specialization in Multimodal Transformers","created":"2025-10-24","cited_by_count":17,"area":"mllm"},{"id":"2501.03012","title":"Analyzing Finetuning Representation Shift for Multimodal LLMs Steering","created":"2025-01-06","cited_by_count":16,"area":"mllm"},{"id":"2510.04217","title":"MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering","created":"2025-10-05","cited_by_count":10,"area":"mllm"},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2501.02029","title":"Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models","created":"2025-01-03","cited_by_count":7,"area":"mllm"},{"id":"2403.19837","title":"Concept-based Analysis of Neural Networks via Vision-Language Models","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2602.07025","title":"The Geometry of Representational Failures in Vision Language Models","created":"2026-02-02","cited_by_count":6,"area":"mllm"},{"id":"2509.00373","title":"Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models","created":"2025-08-30","cited_by_count":5,"area":"mllm"},{"id":"2606.13870","title":"Mirage Probes: How Vision Models Fake Visual Understanding","created":"2026-06-11","cited_by_count":5,"area":"mllm"},{"id":"2504.03735","title":"Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots","created":"2025-04-01","cited_by_count":4,"area":"mllm"},{"id":"2603.06054","title":"Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving","created":"2026-03-06","cited_by_count":3,"area":"mllm"},{"id":"2507.12950","title":"Insights into a radiology-specialised multimodal large language model with sparse autoencoders","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2505.17132","title":"Dynamic Token Reweighting for Robust Vision-Language Models","created":"2025-05-22","cited_by_count":1,"area":"mllm"},{"id":"2510.02528","title":"Multimodal Function Vectors for Visual Relations","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"id":"2605.07148","title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2605.15687","title":"ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models","created":"2026-05-15","cited_by_count":1,"area":"mllm"},{"id":"2606.14758","title":"Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2602.05096","title":"Visual concept ranking uncovers medical shortcuts used by large multimodal models","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2605.14530","title":"Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2605.14893","title":"Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2606.29888","title":"Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.02494","title":"Towards Robustness against Typographic Attack with Training-free Concept Localization","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2607.03365","title":"Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2607.15851","title":"Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction","created":"2026-07-17","cited_by_count":0,"area":"mllm"},{"id":"2607.21300","title":"Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning","created":"2026-07-23","cited_by_count":0,"area":"mllm"},{"id":"2609.26513","title":"Virtual Encoders in Multimodal Transformers","created":"2026-09-22","cited_by_count":0,"area":"mllm"}],"next_cursor":null}