{"total":119,"rows":[{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39,"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":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32,"area":"mechinterp"},{"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":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2412.18645","title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","created":"2024-12-24","cited_by_count":15,"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":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2505.24492","title":"Object Centric Concept Bottlenecks","created":"2025-05-30","cited_by_count":10,"area":null},{"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":"2407.17827","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2412.18123","title":"AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2509.25638","title":"Generalized Contrastive Learning for Universal Multimodal Retrieval","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2411.00246","title":"ResiDual Transformer Alignment with Spectral Decomposition","created":"2024-10-31","cited_by_count":6,"area":null},{"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":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2506.13831","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","created":"2025-06-16","cited_by_count":6,"area":null},{"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":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","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":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","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":"2511.22170","title":"Partially Shared Concept Bottleneck Models","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2502.09018","title":"Zero-shot Concept Bottleneck Models","created":"2025-02-13","cited_by_count":4,"area":null},{"id":"2506.17265","title":"SUA: Stealthy Multimodal Large Language Model Unlearning Attack","created":"2025-06-10","cited_by_count":4,"area":"mllm"},{"id":"2405.19146","title":"I Bet You Did Not Mean That: Testing Semantic Importance via Betting","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2406.08377","title":"DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2508.19195","title":"All-in-One Slider for Attribute Manipulation in Diffusion Models","created":"2025-08-26","cited_by_count":3,"area":"diffusion"},{"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":"2509.01910","title":"Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2509.05309","title":"ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders","created":"2025-08-26","cited_by_count":3,"area":"mechinterp"},{"id":"2511.12331","title":"SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models","created":"2025-11-15","cited_by_count":3,"area":"mllm"},{"id":"2511.12978","title":"Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach","created":"2025-11-17","cited_by_count":3,"area":"mllm"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2603.28211","title":"Explaining CLIP Zero-shot Predictions Through Concepts","created":"2026-03-30","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":"2403.04125","title":"ComFe: An Interpretable Head for Vision Transformers","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2407.08689","title":"Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2502.16733","title":"Coreset Selection via LLM-based Concept Bottlenecks","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.21307","title":"The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models","created":"2025-04-30","cited_by_count":2,"area":"diffusion"},{"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":"2507.17456","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","created":"2025-07-23","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":"2512.17178","title":"ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","cited_by_count":2,"area":"mechinterp"},{"id":"2602.20853","title":"On the Explainability of Vision-Language Models in Art History","created":"2026-02-24","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":"2605.13675","title":"Characterizing Universal Object Representations Across Vision Models","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2503.12875","title":"An interpretable approach to automating the assessment of biofouling in video footage","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2503.19902","title":"ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models","created":"2025-03-25","cited_by_count":1,"area":"diffusion"},{"id":"2504.10004","title":"An Image is Worth $K$ Topics: A Visual Structural Topic Model with Pretrained Image Embeddings","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2508.14280","title":"Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference","created":"2025-08-19","cited_by_count":1,"area":"mllm"},{"id":"2508.20322","title":"Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2512.07245","title":"Zero-Shot Textual Explanations via Translating Decision-Critical Features","created":"2025-12-08","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":"2602.18867","title":"Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning","created":"2026-02-21","cited_by_count":1,"area":null},{"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":"2604.17327","title":"Signal or Noise in Multi-Agent LLM-based Stock Recommendations?","created":"2026-04-19","cited_by_count":1,"area":"agents"},{"id":"2605.06610","title":"SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.06640","title":"Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.07148","title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2606.18839","title":"Semantic Robustness Certification for Vision-Language Models","created":"2026-06-17","cited_by_count":1,"area":"mllm"},{"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":"2411.15239","title":"Preserving Angles Improves Feature Distillation","created":"2024-11-22","cited_by_count":0,"area":"distill"},{"id":"2503.17285","title":"An Iterative Feedback Mechanism for Improving Natural Language Class Descriptions in Open-Vocabulary Object Detection","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2503.21277","title":"Zero-Shot Visual Concept Blending Without Text Guidance","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2505.21595","title":"Relevance-driven Input Dropout: an Explanation-guided Regularization Technique","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2507.00537","title":"Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2507.03542","title":"Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor","created":"2025-07-04","cited_by_count":0,"area":"mllm"},{"id":"2507.07532","title":"Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2509.01453","title":"Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.17522","title":"Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2509.18111","title":"Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detection","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.19943","title":"Interpreting ResNet-based CLIP via Neuron-Attention Decomposition","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.22035","title":"Caption-Driven Explainability: Probing CNNs for Bias via CLIP","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.00110","title":"Chain of Time: In-Context Physical Simulation with Image Generation Models","created":"2025-10-30","cited_by_count":0,"area":"mllm"},{"id":"2602.00924","title":"Supervised sparse auto-encoders for interpretable and compositional representations","created":"2026-01-31","cited_by_count":0,"area":"mechinterp"},{"id":"2602.15650","title":"Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation","created":"2026-02-17","cited_by_count":0,"area":"mllm"},{"id":"2603.26328","title":"Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.26798","title":"Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2603.29654","title":"Concept frustration: Aligning human concepts and machine representations","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.05971","title":"Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2604.11868","title":"MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs","created":"2026-04-13","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":"2604.18109","title":"FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.05329","title":"Understanding Annotator Safety Policy with Interpretability","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.07257","title":"Adaptive Subspace Projection for Generative Personalization","created":"2026-05-08","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":"2605.14309","title":"ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.11661","title":"Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.19489","title":"Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks","created":"2026-06-17","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}