{"total":16,"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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"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":"2512.07730","title":"SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination","created":"2025-12-08","cited_by_count":5,"area":"mllm"},{"id":"2604.07802","title":"Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models","created":"2026-04-09","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":"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":"2603.07335","title":"VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models","created":"2026-03-07","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":"2604.04473","title":"Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks","created":"2026-04-06","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":"2608.24142","title":"What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2609.04276","title":"FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2610.00848","title":"Geometric Similarity in VLM Low-Level Vision Representations","created":"2026-10-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}