{"total":58,"rows":[{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236,"area":"diffusion"},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218,"area":"mllm"},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2504.08729","title":"Steering CLIP's vision transformer with sparse autoencoders","created":"2025-04-11","cited_by_count":38,"area":"mechinterp"},{"id":"2304.04512","title":"Defense-Prefix for Preventing Typographic Attacks on CLIP","created":"2023-04-10","cited_by_count":24,"area":"mllm"},{"id":"2303.15441","title":"Zero-shot Model Diagnosis","created":"2023-03-27","cited_by_count":23,"area":null},{"id":"2412.00114","title":"SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments","created":"2024-11-28","cited_by_count":22,"area":"mllm"},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2503.12127","title":"Hyperbolic Safety-Aware Vision-Language Models","created":"2025-03-15","cited_by_count":17,"area":"mllm"},{"id":"2406.14562","title":"Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2410.07336","title":"Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training","created":"2024-10-09","cited_by_count":16,"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":"2310.16781","title":"Kiki or Bouba? Sound Symbolism in Vision-and-Language Models","created":"2023-10-25","cited_by_count":14,"area":null},{"id":"2504.04893","title":"SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models","created":"2025-04-07","cited_by_count":13,"area":"mllm"},{"id":"2311.16254","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2305.14053","title":"Parts of Speech-Grounded Subspaces in Vision-Language Models","created":"2023-05-23","cited_by_count":11,"area":"mllm"},{"id":"2503.22912","title":"DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID","created":"2025-03-28","cited_by_count":11,"area":null},{"id":"2506.06231","title":"Towards an Explainable Comparison and Alignment of Feature Embeddings","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2402.02346","title":"Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback","created":"2024-02-04","cited_by_count":9,"area":"diffusion"},{"id":"2212.04412","title":"Task Bias in Vision-Language Models","created":"2022-12-08","cited_by_count":8,"area":"mllm"},{"id":"2505.22854","title":"CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2601.03714","title":"Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR","created":"2026-01-07","cited_by_count":8,"area":null},{"id":"2408.00441","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2408.07080","title":"DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning","created":"2024-08-05","cited_by_count":6,"area":"distill"},{"id":"2309.08928","title":"In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval","created":"2023-09-16","cited_by_count":5,"area":"mllm"},{"id":"2404.02990","title":"ASAP: Interpretable Analysis and Summarization of AI-generated Image Patterns at Scale","created":"2024-04-03","cited_by_count":5,"area":"diffusion"},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2411.08923","title":"Aligning Visual Contrastive learning models via Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2505.24361","title":"Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation","created":"2025-05-30","cited_by_count":4,"area":"distill"},{"id":"2303.09270","title":"SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective","created":"2023-03-16","cited_by_count":3,"area":"mllm"},{"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":"2408.04102","title":"ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2411.07691","title":"New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2503.13652","title":"Web Artifact Attacks Disrupt Vision Language Models","created":"2025-03-17","cited_by_count":2,"area":"mllm"},{"id":"2503.21541","title":"LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2512.11899","title":"Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models","created":"2025-12-10","cited_by_count":2,"area":"mllm"},{"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":"2403.03408","title":"Scene Depth Estimation from Traditional Oriental Landscape Paintings","created":"2024-03-06","cited_by_count":0,"area":null},{"id":"2405.14030","title":"Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2412.01725","title":"Attacks on multimodal models","created":"2024-12-02","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":"2506.19389","title":"Emergence of Text Readability in Vision Language Models","created":"2025-06-24","cited_by_count":0,"area":"mllm"},{"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":"2510.01004","title":"TextCAM: Explaining Class Activation Map with Text","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2604.04473","title":"Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks","created":"2026-04-06","cited_by_count":0,"area":"mllm"},{"id":"2607.00858","title":"MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment","created":"2026-07-01","cited_by_count":0,"area":null},{"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":"2609.18823","title":"Using OCR Heads to Verbalize Image Semantics","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.27371","title":"ASAP: Visual Analytics for Identifying and Analyzing Image Patterns in AI-generated Images","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.13252","title":"Vision Transformers Learn Word Meaning from Images Alone","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}