{"total":36,"rows":[{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"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":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"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":"2602.00462","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","created":"2026-01-31","cited_by_count":15,"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":"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":"2603.22278","title":"The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models","created":"2026-03-23","cited_by_count":4,"area":"mllm"},{"id":"2601.08017","title":"Representations of Text and Images Align From Layer One","created":"2026-01-12","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":"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":"2606.00435","title":"Detect Before You Leap: Mirage Detection in Vision-Language Models","created":"2026-05-29","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":"2409.15806","title":"CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation","created":"2024-09-24","cited_by_count":0,"area":"mllm"},{"id":"2504.16047","title":"Evaluating Vision Language Models (VLMs) for Radiology: A Comprehensive Analysis","created":"2025-04-22","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":"2603.27070","title":"Structural Graph Probing of Vision-Language Models","created":"2026-03-28","cited_by_count":0,"area":"mllm"},{"id":"2604.18203","title":"Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs","created":"2026-04-20","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":"2606.01679","title":"Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification","created":"2026-06-01","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":"2608.06154","title":"Visual Grounding in Zero-Shot Vision-Language Control","created":"2026-08-06","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":"2608.20763","title":"CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2608.30750","title":"Do VLMs Share Safety Neurons Across Modalities?","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.04336","title":"MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering","created":"2026-09-03","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":"2609.18860","title":"Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection","created":"2026-09-16","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":"2610.13910","title":"When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors","created":"2026-10-09","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"}],"next_cursor":null}