{"total":62,"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":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113,"area":"mllm"},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"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":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39,"area":"mllm"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26,"area":"mllm"},{"id":"2406.10995","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","created":"2024-06-16","cited_by_count":24,"area":"mllm"},{"id":"2409.17143","title":"Attention Prompting on Image for Large Vision-Language Models","created":"2024-09-25","cited_by_count":23,"area":"mllm"},{"id":"2504.21447","title":"Multimodal Language Models See Better When They Look Shallower","created":"2025-04-30","cited_by_count":23,"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":"2510.04819","title":"Visual Representations inside the Language Model","created":"2025-10-06","cited_by_count":15,"area":"mllm"},{"id":"2511.22697","title":"Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations","created":"2025-11-27","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":"2411.10950","title":"Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering","created":"2024-11-17","cited_by_count":11,"area":"mllm"},{"id":"2407.18999","title":"Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models","created":"2024-07-26","cited_by_count":10,"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":"2411.12044","title":"ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements","created":"2024-11-18","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":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"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":"2508.16652","title":"Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability","created":"2025-08-20","cited_by_count":4,"area":"mllm"},{"id":"2602.20423","title":"MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation","created":"2026-02-23","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":"2506.05439","title":"LLMs Can Compensate for Deficiencies in Visual Representations","created":"2025-06-05","cited_by_count":3,"area":"mllm"},{"id":"2509.03740","title":"CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values","created":"2025-09-03","cited_by_count":3,"area":"mllm"},{"id":"2603.19862","title":"IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment","created":"2026-03-20","cited_by_count":3,"area":"mllm"},{"id":"2603.28211","title":"Explaining CLIP Zero-shot Predictions Through Concepts","created":"2026-03-30","cited_by_count":3,"area":"mllm"},{"id":"2503.19670","title":"fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models","created":"2025-03-25","cited_by_count":2,"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":"2510.26466","title":"Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition","created":"2025-10-30","cited_by_count":2,"area":"mllm"},{"id":"2601.03100","title":"TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs","created":"2026-01-06","cited_by_count":2,"area":"mllm"},{"id":"2607.25125","title":"LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos","created":"2026-07-27","cited_by_count":2,"area":"mllm"},{"id":"2609.06079","title":"LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies","created":"2026-09-05","cited_by_count":2,"area":"mllm"},{"id":"2503.23495","title":"Embedding Shift Dissection on CLIP: Effects of Augmentations on VLM's Representation Learning","created":"2025-03-30","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":"2603.01111","title":"DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles","created":"2026-03-01","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":"2603.06302","title":"DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models","created":"2026-03-06","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":"2606.16193","title":"Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs","created":"2026-06-15","cited_by_count":1,"area":"mllm"},{"id":"2606.18008","title":"PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution","created":"2026-06-16","cited_by_count":1,"area":"mllm"},{"id":"2607.23271","title":"What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2608.06901","title":"Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models","created":"2026-08-07","cited_by_count":1,"area":"mllm"},{"id":"2608.28383","title":"Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2502.15389","title":"The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting","created":"2025-02-21","cited_by_count":0,"area":"mllm"},{"id":"2506.19389","title":"Emergence of Text Readability in Vision Language Models","created":"2025-06-24","cited_by_count":0,"area":"mllm"},{"id":"2508.12877","title":"Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning","created":"2025-08-18","cited_by_count":0,"area":"mllm"},{"id":"2509.26235","title":"Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2602.15650","title":"Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation","created":"2026-02-17","cited_by_count":0,"area":"mllm"},{"id":"2603.12799","title":"What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models","created":"2026-03-13","cited_by_count":0,"area":"mllm"},{"id":"2603.27176","title":"MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence","created":"2026-03-28","cited_by_count":0,"area":"mllm"},{"id":"2605.14309","title":"ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2606.25160","title":"Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding","created":"2026-06-23","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":"2608.09928","title":"Multimodal Model Diffing for Feature Discovery and Control","created":"2026-08-10","cited_by_count":0,"area":"mllm"},{"id":"2610.06932","title":"RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation","created":"2026-10-03","cited_by_count":0,"area":"mllm"}],"next_cursor":null}