{"total":68,"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":"2504.08729","title":"Steering CLIP's vision transformer with sparse autoencoders","created":"2025-04-11","cited_by_count":38,"area":"mechinterp"},{"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":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21,"area":"mechinterp"},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2506.15963","title":"On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy","created":"2025-06-19","cited_by_count":14,"area":"mechinterp"},{"id":"2601.22515","title":"DNA: Uncovering Universal Latent Forgery Knowledge","created":"2026-01-30","cited_by_count":14,"area":null},{"id":"2510.21323","title":"VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set","created":"2025-10-24","cited_by_count":13,"area":"lr"},{"id":"2507.12464","title":"CytoSAE: Interpretable Cell Embeddings for Hematology","created":"2025-07-16","cited_by_count":8,"area":"mechinterp"},{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2602.05027","title":"AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders","created":"2026-02-04","cited_by_count":8,"area":"mechinterp"},{"id":"2505.20229","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","created":"2025-05-26","cited_by_count":6,"area":"mechinterp"},{"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":"2509.00749","title":"Causal Interpretation of Sparse Autoencoder Features in Vision","created":"2025-08-31","cited_by_count":5,"area":"mechinterp"},{"id":"2509.24510","title":"Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2510.26186","title":"ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts","created":"2025-10-30","cited_by_count":5,"area":null},{"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":"2605.10815","title":"Probing Cross-modal Information Hubs in Audio-Visual LLMs","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2505.06745","title":"Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers","created":"2025-05-10","cited_by_count":3,"area":null},{"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":"2606.06664","title":"Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2506.01247","title":"Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering","created":"2025-06-02","cited_by_count":2,"area":"mechinterp"},{"id":"2507.15227","title":"Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders","created":"2025-07-21","cited_by_count":2,"area":"mechinterp"},{"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":"2603.22593","title":"Language Models Can Explain Visual Features via Steering","created":"2026-03-23","cited_by_count":2,"area":"mechinterp"},{"id":"2604.14925","title":"Improving Sparse Autoencoder with Dynamic Attention","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"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":"2606.07473","title":"Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders","created":"2026-06-05","cited_by_count":2,"area":"mechinterp"},{"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":"2506.10085","title":"VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models","created":"2025-06-11","cited_by_count":1,"area":"lr"},{"id":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2509.20376","title":"ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language Models","created":"2025-09-20","cited_by_count":1,"area":"mechinterp"},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2512.15938","title":"SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks","created":"2025-12-17","cited_by_count":1,"area":"mechinterp"},{"id":"2512.18930","title":"LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer","created":"2025-12-22","cited_by_count":1,"area":"mechinterp"},{"id":"2602.07311","title":"LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery","created":"2026-02-07","cited_by_count":1,"area":"mechinterp"},{"id":"2602.12403","title":"MonoLoss: A Training Objective for Interpretable Monosemantic Representations","created":"2026-02-12","cited_by_count":1,"area":"mechinterp"},{"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":"2603.13884","title":"SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis","created":"2026-03-14","cited_by_count":1,"area":"lr"},{"id":"2604.05724","title":"Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP","created":"2026-04-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"},{"id":"2605.01829","title":"GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models","created":"2026-05-03","cited_by_count":1,"area":"mechinterp"},{"id":"2605.17504","title":"A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle","created":"2026-05-17","cited_by_count":1,"area":"mechinterp"},{"id":"2605.24946","title":"Interpretability Transfer from Language to Vision via Sparse Autoencoders","created":"2026-05-24","cited_by_count":1,"area":"mechinterp"},{"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":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2509.22015","title":"Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders","created":"2025-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2603.26743","title":"Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)","created":"2026-03-23","cited_by_count":0,"area":"mechinterp"},{"id":"2604.03919","title":"Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders","created":"2026-04-05","cited_by_count":0,"area":"mechinterp"},{"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":"2604.13304","title":"Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision","created":"2026-04-14","cited_by_count":0,"area":"mechinterp"},{"id":"2607.06328","title":"Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models","created":"2026-07-07","cited_by_count":0,"area":"driving"},{"id":"2607.24706","title":"SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotations","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.03008","title":"V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.09928","title":"Multimodal Model Diffing for Feature Discovery and Control","created":"2026-08-10","cited_by_count":0,"area":"mllm"},{"id":"2608.14922","title":"SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable","created":"2026-08-14","cited_by_count":0,"area":"mechinterp"},{"id":"2608.20117","title":"SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events","created":"2026-08-20","cited_by_count":0,"area":"mechinterp"},{"id":"2608.20134","title":"Feature Evolution and Migration during Vision Transformer Training","created":"2026-08-20","cited_by_count":0,"area":"mechinterp"},{"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":"2609.17152","title":"ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers","created":"2026-09-15","cited_by_count":0,"area":"mechinterp"},{"id":"2609.35020","title":"Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2610.00848","title":"Geometric Similarity in VLM Low-Level Vision Representations","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.03498","title":"Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models","created":"2026-10-02","cited_by_count":0,"area":"vla"},{"id":"2610.13992","title":"How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}