{"total":104,"rows":[{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143,"area":"mllm"},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122,"area":"mllm"},{"id":"2503.06287","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","created":"2025-03-08","cited_by_count":83,"area":"mllm"},{"id":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"area":"diffusion"},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2411.17491","title":"What's in the Image? A Deep-Dive into the Vision of Vision Language Models","created":"2024-11-26","cited_by_count":68,"area":"mllm"},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50,"area":null},{"id":"2503.06169","title":"Treble Counterfactual VLMs: A Causal Approach to Hallucination","created":"2025-03-08","cited_by_count":35,"area":"mllm"},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2505.01481","title":"VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding","created":"2025-05-02","cited_by_count":32,"area":"mllm"},{"id":"2505.17127","title":"Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts","created":"2025-05-21","cited_by_count":32,"area":"mllm"},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2506.11976","title":"How Visual Representations Map to Language Feature Space in Multimodal LLMs","created":"2025-06-13","cited_by_count":25,"area":"lr"},{"id":"2411.19187","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","created":"2024-11-28","cited_by_count":22,"area":"mllm"},{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2502.15969","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","created":"2025-02-21","cited_by_count":16,"area":"lr"},{"id":"2503.07050","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation","created":"2025-03-10","cited_by_count":16,"area":"diffusion"},{"id":"2503.08908","title":"Interpreting the Repeated Token Phenomenon in Large Language Models","created":"2025-03-11","cited_by_count":16,"area":null},{"id":"2509.22496","title":"Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation","created":"2025-09-26","cited_by_count":16,"area":"mllm"},{"id":"2503.07772","title":"Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs","created":"2025-03-10","cited_by_count":15,"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":"2510.04819","title":"Visual Representations inside the Language Model","created":"2025-10-06","cited_by_count":15,"area":"mllm"},{"id":"2602.00462","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","created":"2026-01-31","cited_by_count":15,"area":"mllm"},{"id":"2601.12626","title":"Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models","created":"2026-01-18","cited_by_count":14,"area":"lr"},{"id":"2412.14133","title":"Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models","created":"2024-12-18","cited_by_count":12,"area":"lr"},{"id":"2507.13868","title":"When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models","created":"2025-07-18","cited_by_count":11,"area":"mllm"},{"id":"2508.19972","title":"GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity","created":"2025-08-27","cited_by_count":11,"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":"2509.21379","title":"SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders","created":"2025-09-23","cited_by_count":10,"area":"diffusion"},{"id":"2503.20252","title":"LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2511.20032","title":"Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2601.05547","title":"VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck","created":"2026-01-09","cited_by_count":8,"area":"mllm"},{"id":"2505.12343","title":"Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models","created":"2025-05-18","cited_by_count":7,"area":"mllm"},{"id":"2512.03276","title":"Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2512.18813","title":"Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction","created":"2025-12-21","cited_by_count":7,"area":"mllm"},{"id":"2602.05535","title":"Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification","created":"2026-02-05","cited_by_count":6,"area":"mllm"},{"id":"2602.24014","title":"Interpretable Debiasing of Vision-Language Models for Social Fairness","created":"2026-02-27","cited_by_count":6,"area":"lr"},{"id":"2505.21547","title":"Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing","created":"2025-05-24","cited_by_count":5,"area":"mllm"},{"id":"2505.21967","title":"Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack","created":"2025-05-28","cited_by_count":5,"area":"mllm"},{"id":"2505.22200","title":"Investigating Mechanisms for In-Context Vision Language Binding","created":"2025-05-28","cited_by_count":5,"area":"mllm"},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5,"area":"mllm"},{"id":"2512.07730","title":"SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination","created":"2025-12-08","cited_by_count":5,"area":"mllm"},{"id":"2603.12989","title":"Test-Time Attention Purification for Backdoored Large Vision Language Models","created":"2026-03-13","cited_by_count":5,"area":"mllm"},{"id":"2502.14888","title":"Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models","created":"2025-02-16","cited_by_count":4,"area":"mllm"},{"id":"2505.17425","title":"Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.09522","title":"Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding","created":"2025-06-11","cited_by_count":4,"area":"mllm"},{"id":"2507.03123","title":"Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations","created":"2025-07-03","cited_by_count":4,"area":"mllm"},{"id":"2509.21997","title":"Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors","created":"2025-09-26","cited_by_count":4,"area":"mllm"},{"id":"2509.24072","title":"Uncovering Grounding IDs: How External Cues Shape Multimodal Binding","created":"2025-09-28","cited_by_count":4,"area":"mllm"},{"id":"2510.03903","title":"Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2602.15556","title":"Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs","created":"2026-02-17","cited_by_count":4,"area":"lr"},{"id":"2603.22278","title":"The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models","created":"2026-03-23","cited_by_count":4,"area":"mllm"},{"id":"2603.29676","title":"A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models","created":"2026-03-31","cited_by_count":4,"area":"mllm"},{"id":"2608.07302","title":"Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination","created":"2026-08-07","cited_by_count":4,"area":"mllm"},{"id":"2504.10786","title":"Visual Language Models show widespread visual deficits on neuropsychological tests","created":"2025-04-15","cited_by_count":3,"area":"lr"},{"id":"2507.14819","title":"Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2604.04863","title":"Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations","created":"2026-04-06","cited_by_count":3,"area":"lr"},{"id":"2606.28273","title":"Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models","created":"2026-06-26","cited_by_count":3,"area":"mllm"},{"id":"2509.19191","title":"Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models","created":"2025-09-23","cited_by_count":2,"area":"mllm"},{"id":"2606.06890","title":"Diagnosing Visual Ignorance in Vision-Language Models","created":"2026-06-05","cited_by_count":2,"area":"mllm"},{"id":"2607.05978","title":"Propose and Attend: Training-free MLLM Grounding Confidence via Multi-Token Localized Attention","created":"2026-07-07","cited_by_count":2,"area":"mllm"},{"id":"2505.24649","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","created":"2025-05-30","cited_by_count":1,"area":"mllm"},{"id":"2506.18887","title":"Steering Conceptual Bias via Transformer Latent-Subspace Activation","created":"2025-06-23","cited_by_count":1,"area":"mechinterp"},{"id":"2510.06292","title":"ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2511.11502","title":"PAS : Prelim Attention Score for Detecting Object Hallucinations in Large Vision--Language Models","created":"2025-11-14","cited_by_count":1,"area":"mllm"},{"id":"2512.00725","title":"ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2601.00269","title":"FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering","created":"2026-01-01","cited_by_count":1,"area":"mllm"},{"id":"2601.23041","title":"One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2602.08713","title":"Towards Understanding Multimodal Fine-Tuning: Spatial Features","created":"2026-02-06","cited_by_count":1,"area":"mllm"},{"id":"2605.12258","title":"Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language Models","created":"2026-05-12","cited_by_count":1,"area":"mllm"},{"id":"2605.19792","title":"Mechanisms of Object Localization in Vision-Language Models","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2507.19420","title":"CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2602.01530","title":"Logit Lens Supervision for Patch-Level Explanations in Vision-Language Models","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2602.04356","title":"Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"id":"2603.16558","title":"Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2603.29405","title":"Hallucination-aware intermediate representation edit in large vision-language models","created":"2026-03-31","cited_by_count":0,"area":"lr"},{"id":"2604.06165","title":"HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2604.12582","title":"Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.16462","title":"From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration","created":"2026-04-08","cited_by_count":0,"area":"mllm"},{"id":"2605.21980","title":"Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.26656","title":"DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2605.31312","title":"Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.20077","title":"The Hidden Evolution of Disguised Visual Context inside the VLM","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.06445","title":"Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.26913","title":"Prior Directions: Why GUI Grounding Gets Locked in the Past","created":"2026-07-29","cited_by_count":0,"area":"mllm"},{"id":"2608.05616","title":"TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.09928","title":"Multimodal Model Diffing for Feature Discovery and Control","created":"2026-08-10","cited_by_count":0,"area":"mllm"},{"id":"2608.10835","title":"UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.11474","title":"Test-Time Hallucination Control in Large Vision-Language Models","created":"2026-08-11","cited_by_count":0,"area":"mllm"},{"id":"2608.19075","title":"ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models","created":"2026-08-19","cited_by_count":0,"area":"mllm"},{"id":"2608.21819","title":"PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models","created":"2026-08-22","cited_by_count":0,"area":"mllm"},{"id":"2608.30480","title":"VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2608.30705","title":"VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.03429","title":"When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.13254","title":"(How) Do MLLMs Report Bistable Images Like Humans?","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":"100"}