{"total":93,"rows":[{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2402.17417","title":"CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification","created":"2024-02-27","cited_by_count":40,"area":null},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2404.05729","title":"Finding Visual Task Vectors","created":"2024-04-08","cited_by_count":24,"area":null},{"id":"2406.01583","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","cited_by_count":18,"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":"2310.10591","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2402.11816","title":"Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2407.05578","title":"FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"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":"2411.00132","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2411.00246","title":"ResiDual Transformer Alignment with Spectral Decomposition","created":"2024-10-31","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":"2509.20345","title":"General Synthetic-Powered Inference","created":"2025-09-24","cited_by_count":6,"area":null},{"id":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2312.11548","title":"Learning Interpretable Queries for Explainable Image Classification with Information Pursuit","created":"2023-12-16","cited_by_count":5,"area":null},{"id":"2406.18344","title":"AlignedCut: Visual Concepts Discovery on Brain-Guided Universal Feature Space","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2503.15699","title":"Representational Similarity via Interpretable Visual Concepts","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2505.15217","title":"Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2510.04564","title":"Conditional Representation Learning for Customized Tasks","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2512.08560","title":"BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain","created":"2025-12-09","cited_by_count":5,"area":null},{"id":"2409.17663","title":"Explanation Bottleneck Models","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2503.20301","title":"Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2505.17425","title":"Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.00698","title":"Concept-Centric Token Interpretation for Vector-Quantized Generative Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2404.02949","title":"The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability","created":"2024-04-03","cited_by_count":3,"area":null},{"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":"2406.09166","title":"Fine-Grained Domain Generalization with Feature Structuralization","created":"2024-06-13","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":"2409.06579","title":"Quantifying and Enabling the Interpretability of CLIP-like Models","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2412.07802","title":"Language Model as Visual Explainer","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2501.06708","title":"Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2502.14889","title":"Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability","created":"2025-02-16","cited_by_count":3,"area":null},{"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":"2501.05205","title":"Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2506.10182","title":"Improving Personalized Search with Regularized Low-Rank Parameter Updates","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2508.17750","title":"From Global to Local: Social Bias Transfer in CLIP","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2509.08940","title":"Discovering Divergent Representations between Text-to-Image Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2510.21704","title":"Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2510.24105","title":"Enhancing Pre-trained Representation Classifiability can Boost its Interpretability","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2603.11793","title":"Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2607.26228","title":"Steering Instruction Hierarchies at Inference Time","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2412.07226","title":"Attention Head Purification: A New Perspective to Harness CLIP for Domain Generalization","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2503.11103","title":"Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2507.04508","title":"Adapter-state Sharing CLIP for Parameter-efficient Multimodal Sarcasm Detection","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2508.00784","title":"Unraveling Hidden Representations: A Multi-Modal Layer Analysis for Better Synthetic Content Forensics","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2508.20322","title":"Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2510.23894","title":"Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation","created":"2025-10-27","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":"2602.12381","title":"Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cues","created":"2026-02-12","cited_by_count":1,"area":null},{"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":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"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":"2505.22259","title":"Domain Adaptation of Attention Heads for Zero-shot Anomaly Detection","created":"2025-05-28","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":"2509.14664","title":"Attention Lattice Adapter: Visual Explanation Generation for Visual Foundation Model","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.19391","title":"TensLoRA: Tensor Alternatives for Low-Rank Adaptation","created":"2025-09-22","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":"2510.01004","title":"TextCAM: Explaining Class Activation Map with Text","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"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":"2605.16877","title":"Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2607.10023","title":"Local Multimodal Music Alignment from Global Supervision","created":"2026-07-10","cited_by_count":0,"area":null},{"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":"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":"2608.21486","title":"EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25609","title":"On the Separation of Human and AI-Generated Images in CLIP Embedding Space","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04800","title":"Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.18823","title":"Using OCR Heads to Verbalize Image Semantics","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03370","title":"LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06919","title":"Anchor Divergence for Semantic Geometry in Contrastive Learning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06928","title":"Metonymic Circuits for Abstract Concept Grounding in Vision Transformers","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}