{"total":37,"rows":[{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"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":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"area":null},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2211.09790","title":"ConStruct-VL: Data-Free Continual Structured VL Concepts Learning","created":"2022-11-17","cited_by_count":20,"area":null},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2502.19842","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2209.03648","title":"FETA: Towards Specializing Foundation Models for Expert Task Applications","created":"2022-09-08","cited_by_count":13,"area":null},{"id":"2304.12539","title":"Text-guided Eyeglasses Manipulation with Spatial Constraints","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2403.02875","title":"Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2404.15721","title":"SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2407.15296","title":"Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","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":"2512.21150","title":"ORCA: Object Recognition and Comprehension for Archiving Marine Species","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2408.09511","title":"NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2601.22570","title":"Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2607.12290","title":"The Sound of Absence: Audio-Language Embedding Models Struggle with Negation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2503.13021","title":"Dynamic Relation Inference via Verb Embeddings","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2607.00428","title":"HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.21998","title":"Medical-Checklist: Assessing the Comprehension of Medical Images by Multimodal Models","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.27857","title":"EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.00726","title":"Foveated Probes Recover Localized Binding Information in Vision Foundation Models","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.32462","title":"Can Motion-Language Models Ground Structure? STRIDE for Evaluating the Evaluators","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33319","title":"PhysAlign: A Benchmark for Evidence-Grounded Role Alignment in Multimodal Physics Reasoning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37230","title":"Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}