{"total":60,"rows":[{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"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":"2601.22515","title":"DNA: Uncovering Universal Latent Forgery Knowledge","created":"2026-01-30","cited_by_count":14,"area":null},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"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":"2509.24559","title":"Emergent World Representations in OpenVLA","created":"2025-09-29","cited_by_count":6,"area":"wm"},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2509.00749","title":"Causal Interpretation of Sparse Autoencoder Features in Vision","created":"2025-08-31","cited_by_count":5,"area":"mechinterp"},{"id":"2510.04136","title":"MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition","created":"2025-10-05","cited_by_count":4,"area":"moe"},{"id":"2508.20040","title":"Model Science: getting serious about verification, explanation and control of AI systems","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2601.08017","title":"Representations of Text and Images Align From Layer One","created":"2026-01-12","cited_by_count":3,"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":"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":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.26411","title":"MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders","created":"2025-10-30","cited_by_count":2,"area":"mechinterp"},{"id":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","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":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.18024","title":"Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2602.08615","title":"Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2602.11448","title":"Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.19028","title":"SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models","created":"2026-03-19","cited_by_count":1,"area":"mllm"},{"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":"2605.06610","title":"SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2606.07451","title":"TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment","created":"2026-06-05","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":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2607.17770","title":"Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence","created":"2026-07-20","cited_by_count":1,"area":"mechinterp"},{"id":"2512.19734","title":"The Deleuzian Representation Hypothesis","created":"2025-12-17","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":"2602.10508","title":"Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.25075","title":"Sparse Visual Thought Circuits in Vision-Language Models","created":"2026-03-26","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":"2605.11107","title":"Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2605.22679","title":"Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"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":"2606.29888","title":"Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.00023","title":"Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders","created":"2026-06-19","cited_by_count":0,"area":"rag"},{"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":"2607.13660","title":"The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model","created":"2026-07-15","cited_by_count":0,"area":null},{"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":"2608.05122","title":"IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.16251","title":"SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.23626","title":"A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts","created":"2026-08-23","cited_by_count":0,"area":null},{"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":"2609.20129","title":"Local Sparsity Enables Unsupervised LLM Safety Detection","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.36294","title":"When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders","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":"2610.00895","title":"Towards Fast and Disentangled Counterfactuals for Visual Foundation Models","created":"2026-10-01","cited_by_count":0,"area":null},{"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":"2610.04020","title":"ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"id":"2610.05794","title":"A Testable Theory of Atomic Features","created":"2026-10-05","cited_by_count":0,"area":"mechinterp"},{"id":"2610.06928","title":"Metonymic Circuits for Abstract Concept Grounding in Vision Transformers","created":"2026-10-03","cited_by_count":0,"area":null},{"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"},{"id":"2610.20139","title":"Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}