{"total":15,"rows":[{"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":"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":"2410.10308","title":"LG-CAV: Train Any Concept Activation Vector with Language Guidance","created":"2024-10-14","cited_by_count":9,"area":"mllm"},{"id":"2410.04819","title":"MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models","created":"2024-10-07","cited_by_count":7,"area":"mllm"},{"id":"2502.18485","title":"Deciphering Functions of Neurons in Vision-Language Models","created":"2025-02-10","cited_by_count":3,"area":"mllm"},{"id":"2601.20075","title":"Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2602.20853","title":"On the Explainability of Vision-Language Models in Art History","created":"2026-02-24","cited_by_count":2,"area":"mllm"},{"id":"2509.21102","title":"Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models","created":"2025-09-25","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":"2603.10781","title":"Taking Shortcuts for Categorical VQA Using Super Neurons","created":"2026-03-11","cited_by_count":0,"area":"mllm"},{"id":"2605.22651","title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining","created":"2026-05-21","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":"2606.30498","title":"On the Faithfulness of Post-Hoc Concept Bottleneck Models","created":"2026-06-29","cited_by_count":0,"area":"mllm"}],"next_cursor":null}