{"total":57,"rows":[{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"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":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2310.07355","title":"IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training","created":"2023-10-11","cited_by_count":23,"area":"mllm"},{"id":"2507.01790","title":"How Do Vision-Language Models Process Conflicting Information Across Modalities?","created":"2025-07-02","cited_by_count":23,"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":"2403.09948","title":"RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training","created":"2024-03-15","cited_by_count":8,"area":"mllm"},{"id":"2412.13871","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer","created":"2024-12-18","cited_by_count":8,"area":"mllm"},{"id":"2509.14837","title":"V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models","created":"2025-09-18","cited_by_count":8,"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":"2504.16727","title":"Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward","created":"2025-04-23","cited_by_count":7,"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":"2606.13870","title":"Mirage Probes: How Vision Models Fake Visual Understanding","created":"2026-06-11","cited_by_count":5,"area":"mllm"},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","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":"2508.18297","title":"Can VLMs Recall Factual Associations From Visual References?","created":"2025-08-22","cited_by_count":3,"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":"2603.11024","title":"Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style","created":"2026-03-11","cited_by_count":3,"area":"mllm"},{"id":"2310.14108","title":"CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement","created":"2023-10-21","cited_by_count":2,"area":"mllm"},{"id":"2505.22664","title":"Zero-Shot Vision Encoder Grafting via LLM Surrogates","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2609.00868","title":"The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence","created":"2026-09-01","cited_by_count":2,"area":"mllm"},{"id":"2512.01148","title":"SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models","created":"2025-11-30","cited_by_count":1,"area":"mllm"},{"id":"2602.23136","title":"Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs","created":"2026-02-26","cited_by_count":1,"area":"mllm"},{"id":"2603.02865","title":"Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language Models","created":"2026-03-03","cited_by_count":1,"area":"mllm"},{"id":"2603.17228","title":"From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2603.24181","title":"Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection","created":"2026-03-25","cited_by_count":1,"area":"mllm"},{"id":"2604.08333","title":"Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification","created":"2026-04-09","cited_by_count":1,"area":"mllm"},{"id":"2605.30170","title":"Unveiling the Visual Counting Bottleneck in Vision-Language Models","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2606.00435","title":"Detect Before You Leap: Mirage Detection in Vision-Language Models","created":"2026-05-29","cited_by_count":1,"area":"mllm"},{"id":"2606.03795","title":"Beyond Compression: Quantifying Spectral Accessibility in Vision Representations","created":"2026-06-02","cited_by_count":1,"area":"mllm"},{"id":"2607.09544","title":"The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs","created":"2026-07-10","cited_by_count":1,"area":"mllm"},{"id":"2608.00345","title":"ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression","created":"2026-07-31","cited_by_count":1,"area":"mllm"},{"id":"2603.06459","title":"Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement","created":"2026-03-06","cited_by_count":0,"area":"mllm"},{"id":"2603.24787","title":"ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2604.00913","title":"Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment","created":"2026-04-01","cited_by_count":0,"area":"mllm"},{"id":"2604.22038","title":"Source-Modality Monitoring in Vision-Language Models","created":"2026-04-23","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":"2605.13322","title":"KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2606.06714","title":"Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception","created":"2026-06-04","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":"2607.20993","title":"Sparse Concept Channels in Frozen 3D CT Vision Encoders","created":"2026-07-23","cited_by_count":0,"area":"mllm"},{"id":"2608.07562","title":"Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation","created":"2026-08-02","cited_by_count":0,"area":"mllm"},{"id":"2608.16263","title":"Seeing Before Answering: Training-Free Visual Layer Profiling for Vision-Language Models","created":"2026-08-17","cited_by_count":0,"area":"mllm"},{"id":"2608.20763","title":"CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2608.20999","title":"Latent Ordinal Evidence, Misaligned Outputs: Inference-Time Ordinal Lens Alignment for Multimodal LLMs","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2609.09124","title":"Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs","created":"2026-09-08","cited_by_count":0,"area":"mllm"},{"id":"2609.09417","title":"Vision-language models know more about agriculture than they show and rubric-grounded verifications close the gap","created":"2026-09-08","cited_by_count":0,"area":"mllm"},{"id":"2609.17790","title":"Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models","created":"2026-09-15","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"},{"id":"2609.32653","title":"From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models","created":"2026-09-26","cited_by_count":0,"area":"mllm"},{"id":"2610.03445","title":"Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally","created":"2026-10-02","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":"2610.13465","title":"When MLLMs miss what humans read: diagnosing and learning to read squint text","created":"2026-10-09","cited_by_count":0,"area":"mllm"},{"id":"2610.17976","title":"Seeing Depth but Choosing Cues in Vision-Language Models","created":"2026-10-13","cited_by_count":0,"area":"mllm"},{"id":"2610.18729","title":"Segment Where You Look: Attention as the Interface Between Language Models and Segmenters","created":"2026-10-13","cited_by_count":0,"area":"mllm"},{"id":"2610.19407","title":"Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers","created":"2026-10-14","cited_by_count":0,"area":"mllm"},{"id":"2610.20107","title":"Why Generate a Click? Plug-in Decision Heads for Web Agents","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}