{"total":71,"rows":[{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2603.19183","title":"Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models","created":"2026-03-19","cited_by_count":16,"area":"vla"},{"id":"2603.19233","title":"Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models","created":"2026-03-19","cited_by_count":15,"area":"vla"},{"id":"2505.20254","title":"Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs","created":"2025-05-26","cited_by_count":14,"area":"mechinterp"},{"id":"2604.09364","title":"Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts","created":"2026-04-10","cited_by_count":11,"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":"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":"2507.13328","title":"Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2602.24014","title":"Interpretable Debiasing of Vision-Language Models for Social Fairness","created":"2026-02-27","cited_by_count":6,"area":"lr"},{"id":"2509.00749","title":"Causal Interpretation of Sparse Autoencoder Features in Vision","created":"2025-08-31","cited_by_count":5,"area":"mechinterp"},{"id":"2605.10815","title":"Probing Cross-modal Information Hubs in Audio-Visual LLMs","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2506.04859","title":"Sparse Autoencoders, Again?","created":"2025-06-05","cited_by_count":3,"area":"mechinterp"},{"id":"2507.20973","title":"Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder","created":"2025-07-28","cited_by_count":3,"area":"diffusion"},{"id":"2602.00621","title":"Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering","created":"2026-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2603.08486","title":"Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images","created":"2026-03-09","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":"2507.12950","title":"Insights into a radiology-specialised multimodal large language model with sparse autoencoders","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","cited_by_count":2,"area":"mechinterp"},{"id":"2602.10216","title":"ELROND: Exploring and decomposing intrinsic capabilities of diffusion models","created":"2026-02-10","cited_by_count":2,"area":"diffusion"},{"id":"2604.14925","title":"Improving Sparse Autoencoder with Dynamic Attention","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"id":"2605.17204","title":"Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies","created":"2026-05-17","cited_by_count":2,"area":"vla"},{"id":"2605.31518","title":"On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders","created":"2026-05-29","cited_by_count":2,"area":"mechinterp"},{"id":"2606.06890","title":"Diagnosing Visual Ignorance in Vision-Language Models","created":"2026-06-05","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":"2606.31257","title":"Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"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":"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":"2604.05724","title":"Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP","created":"2026-04-07","cited_by_count":1,"area":"mechinterp"},{"id":"2604.17941","title":"From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"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":"2605.05151","title":"Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting","created":"2026-05-06","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":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2606.24997","title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2607.14280","title":"DiMaS: Distribution Matching for Steering Vision-Language-Action Models","created":"2026-07-15","cited_by_count":1,"area":"vla"},{"id":"2607.16938","title":"What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning","created":"2026-07-18","cited_by_count":1,"area":"driving"},{"id":"2607.17770","title":"Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence","created":"2026-07-20","cited_by_count":1,"area":"mechinterp"},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2601.09776","title":"TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models","created":"2026-01-14","cited_by_count":0,"area":"mechinterp"},{"id":"2602.06806","title":"RAIGen: Rare Attribute Identification in Text-to-Image Generative Models","created":"2026-02-06","cited_by_count":0,"area":"diffusion"},{"id":"2604.01619","title":"Automatic Image-Level Morphological Trait Annotation for Organismal Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2605.00899","title":"LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.16374","title":"Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning","created":"2026-05-10","cited_by_count":0,"area":"mechinterp"},{"id":"2605.22902","title":"Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.08031","title":"Vision-Language Asymmetry in Bistable Image Captioning","created":"2026-06-06","cited_by_count":0,"area":"mllm"},{"id":"2606.14586","title":"S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning","created":"2026-06-12","cited_by_count":0,"area":"alignment"},{"id":"2606.17010","title":"From Tokens to Policy: Causal and Interpretable Heterogeneous Treatment Effects Identification","created":"2026-06-15","cited_by_count":0,"area":null},{"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":"2607.04593","title":"TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models","created":"2026-07-06","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":"2608.28191","title":"EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders","created":"2026-08-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.02634","title":"Latent Cluster Analysis for Vision-Language-Action Models","created":"2026-09-02","cited_by_count":0,"area":"vla"},{"id":"2609.09055","title":"\"World Knowledge\" in the Weights: Reading Concept Circuits of Vision Transformers","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.18860","title":"Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection","created":"2026-09-16","cited_by_count":0,"area":"mllm"},{"id":"2609.24379","title":"Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity","created":"2026-09-21","cited_by_count":0,"area":"mechinterp"},{"id":"2609.30993","title":"FLIP: Final Layer Inference-Time Probing for Vision-Language Models","created":"2026-09-25","cited_by_count":0,"area":"mllm"},{"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":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38098","title":"NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00848","title":"Geometric Similarity in VLM Low-Level Vision Representations","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.14190","title":"Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models","created":"2026-10-09","cited_by_count":0,"area":"mllm"}],"next_cursor":null}