{"total":21,"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":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2411.14982","title":"Large Multi-modal Models Can Interpret Features in Large Multi-modal Models","created":"2024-11-22","cited_by_count":23,"area":"mllm"},{"id":"2502.17514","title":"SAE-V: Interpreting Multimodal Models for Enhanced Alignment","created":"2025-02-22","cited_by_count":23,"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":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"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":"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":"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":"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":"2605.15961","title":"Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models","created":"2026-05-15","cited_by_count":2,"area":"mllm"},{"id":"2606.21197","title":"Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders","created":"2026-06-19","cited_by_count":2,"area":"mllm"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2510.02528","title":"Multimodal Function Vectors for Visual Relations","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"id":"2603.07335","title":"VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2605.08245","title":"When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models","created":"2026-05-07","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":"2601.12809","title":"Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data","created":"2026-01-19","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":"2607.02494","title":"Towards Robustness against Typographic Attack with Training-free Concept Localization","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2607.03738","title":"Attending to Multimodal Generation One Token at a Time","created":"2026-07-04","cited_by_count":0,"area":"mllm"}],"next_cursor":null}