{"total":25,"rows":[{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2503.24267","title":"FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics","created":"2025-03-31","cited_by_count":11,"area":null},{"id":"2408.10593","title":"An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs","created":"2024-08-20","cited_by_count":9,"area":null},{"id":"2503.20252","title":"LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2505.24840","title":"The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2505.16778","title":"Single Domain Generalization for Few-Shot Counting via Universal Representation Matching","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.02671","title":"Test-Time Distillation for Continual Model Adaptation","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2507.03168","title":"Adopting a human developmental visual diet yields robust, shape-based AI vision","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2507.01066","title":"Embedding-based Retrieval in Multimodal Content Moderation","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2605.30062","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2406.03017","title":"DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2406.12757","title":"MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2411.07441","title":"Automatically Detecting Online Deceptive Patterns","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2503.10981","title":"CLIP-Free, Label Free, Unsupervised Concept Bottleneck Models","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2505.16953","title":"ICYM2I: The illusion of multimodal informativeness under missingness","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2511.04161","title":"Seeing Straight: Document Orientation Detection for Efficient OCR","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2602.09475","title":"ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2607.02158","title":"Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2410.06541","title":"Chip-Tuning: Classify Before Language Models Say","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2412.10362","title":"OP-LoRA: The Blessing of Dimensionality","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2505.24340","title":"GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.21769","title":"Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.09935","title":"Unpacking Hateful Memes: Presupposed Context and False Claims","created":"2025-10-11","cited_by_count":0,"area":null}],"next_cursor":null}