{"total":62,"rows":[{"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":"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":"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":"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":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"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":"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":"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":"2508.20040","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":"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":"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":"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":"2605.13675","title":"Characterizing Universal Object Representations Across Vision Models","created":"2026-05-13","cited_by_count":2,"area":null},{"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":"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":"2508.20322","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":"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":"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":"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":"2507.07532","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":"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":"2603.29654","title":"Concept frustration: Aligning human concepts and machine representations","created":"2026-03-31","cited_by_count":0,"area":null},{"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":"2605.29628","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":"2606.19882","title":"Multimodal Concept Bottleneck Models","created":"2026-06-18","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":"2607.22919","title":"Controlling Embedding Spaces with Text-Conditioned Transformations","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.07923","title":"SCoPE: Training-Free Audio-Visual Event Perception via Sparse Cross-Modal Prior Exchange","created":"2026-08-08","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":"2608.25609","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":"2608.29644","title":"Conducting Stylistic Analysis of Paintings through an Art-History Agent","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.34652","title":"Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspective","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38374","title":"Doc2LoRA Provides Decodable Representations of Scientific Ideas","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05518","title":"What Does Fr\\'echet Distance Measure? A Directional Decomposition","created":"2026-10-04","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}],"next_cursor":null}