{"total":53,"rows":[{"id":"2502.03628","title":"The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering","created":"2025-02-05","cited_by_count":66,"area":"mllm"},{"id":"2410.15778","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","created":"2024-10-21","cited_by_count":59,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2505.20977","title":"Evaluating and Steering Modality Preferences in Multimodal Large Language Model","created":"2025-05-27","cited_by_count":33,"area":"mllm"},{"id":"2403.09037","title":"The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?","created":"2024-03-14","cited_by_count":26,"area":"mllm"},{"id":"2410.09047","title":"Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"id":"2502.17514","title":"SAE-V: Interpreting Multimodal Models for Enhanced Alignment","created":"2025-02-22","cited_by_count":23,"area":"mllm"},{"id":"2410.00296","title":"VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild","created":"2024-10-01","cited_by_count":18,"area":"mllm"},{"id":"2502.10486","title":"VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap","created":"2025-02-14","cited_by_count":17,"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":"2508.12815","title":"Learning to Steer: Input-dependent Steering for Multimodal LLMs","created":"2025-08-18","cited_by_count":15,"area":"mllm"},{"id":"2604.09364","title":"Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts","created":"2026-04-10","cited_by_count":11,"area":"mllm"},{"id":"2503.00723","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","created":"2025-03-02","cited_by_count":9,"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":"2410.22888","title":"Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector","created":"2024-10-30","cited_by_count":8,"area":"mllm"},{"id":"2505.12826","title":"Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering","created":"2025-05-19","cited_by_count":8,"area":"mllm"},{"id":"2506.09353","title":"DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt","created":"2025-06-11","cited_by_count":8,"area":"mllm"},{"id":"2602.21704","title":"Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models","created":"2026-02-25","cited_by_count":8,"area":"mllm"},{"id":"2512.05745","title":"ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior","created":"2025-12-05","cited_by_count":7,"area":"mllm"},{"id":"2503.22720","title":"Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models","created":"2025-03-25","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":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2606.14703","title":"Gaze Heads: How VLMs Look at What They Describe","created":"2026-06-12","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":"2602.11824","title":"Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models","created":"2026-02-12","cited_by_count":4,"area":"mllm"},{"id":"2510.22171","title":"HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models","created":"2025-10-25","cited_by_count":3,"area":"mllm"},{"id":"2512.15926","title":"DSO: Direct Steering Optimization for Bias Mitigation","created":"2025-12-17","cited_by_count":3,"area":"mllm"},{"id":"2605.17144","title":"Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States","created":"2026-05-16","cited_by_count":3,"area":"mllm"},{"id":"2507.21637","title":"Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models","created":"2025-07-29","cited_by_count":2,"area":"mllm"},{"id":"2602.22918","title":"Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2606.03093","title":"Decomposing how prompting steers behavior","created":"2026-06-02","cited_by_count":2,"area":"mllm"},{"id":"2502.11427","title":"Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models","created":"2025-02-17","cited_by_count":1,"area":"mllm"},{"id":"2510.09699","title":"VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands","created":"2025-10-09","cited_by_count":1,"area":"mllm"},{"id":"2602.23676","title":"Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering","created":"2026-02-27","cited_by_count":1,"area":"mllm"},{"id":"2605.18104","title":"Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction","created":"2026-05-18","cited_by_count":1,"area":"mllm"},{"id":"2605.23655","title":"CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception","created":"2026-05-22","cited_by_count":1,"area":"mllm"},{"id":"2605.25377","title":"Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation","created":"2026-05-25","cited_by_count":1,"area":"mllm"},{"id":"2608.22916","title":"Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models?","created":"2026-08-24","cited_by_count":1,"area":"mllm"},{"id":"2609.38810","title":"CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models","created":"2026-09-30","cited_by_count":1,"area":"mllm"},{"id":"2411.12590","title":"Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering","created":"2024-11-15","cited_by_count":0,"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":"2605.05593","title":"Causal Probing for Internal Visual Representations in Multimodal Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2607.20993","title":"Sparse Concept Channels in Frozen 3D CT Vision Encoders","created":"2026-07-23","cited_by_count":0,"area":"mllm"},{"id":"2607.26326","title":"Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2608.04483","title":"Not All Redundant Tokens Are Alike: Analyzing Visual Token Pruning through Token Roles","created":"2026-08-05","cited_by_count":0,"area":"mllm"},{"id":"2608.25375","title":"GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2609.24576","title":"What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior","created":"2026-09-21","cited_by_count":0,"area":"mllm"},{"id":"2609.34742","title":"Do Emotion Concepts Generalize Across Sources, Modalities, and Architectures in Vision-Language Models?","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.05129","title":"Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection","created":"2026-10-04","cited_by_count":0,"area":"mllm"},{"id":"2610.07572","title":"Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings","created":"2026-10-06","cited_by_count":0,"area":"mllm"}],"next_cursor":null}