{"total":62,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2401.09865","title":"Improving fine-grained understanding in image-text pre-training","created":"2024-01-18","cited_by_count":44,"area":null},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43,"area":null},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2410.05210","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2404.03539","title":"Is CLIP the main roadblock for fine-grained open-world perception?","created":"2024-04-04","cited_by_count":13,"area":null},{"id":"2305.14998","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2308.01236","title":"Grounded Image Text Matching with Mismatched Relation Reasoning","created":"2023-08-02","cited_by_count":8,"area":null},{"id":"2310.15061","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2405.11685","title":"ColorFoil: Investigating Color Blindness in Large Vision and Language Models","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2502.20104","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2503.09499","title":"MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2507.13328","title":"Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2401.06443","title":"BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining","created":"2024-01-12","cited_by_count":5,"area":null},{"id":"2502.06600","title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","created":"2025-02-10","cited_by_count":5,"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":"2302.12189","title":"HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales","created":"2023-02-23","cited_by_count":4,"area":null},{"id":"2306.16533","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2310.13619","title":"Semi-supervised multimodal coreference resolution in image narrations","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2502.11874","title":"VAQUUM: Are Vague Quantifiers Grounded in Visual Data?","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2504.00942","title":"Experiential Semantic Information and Brain Alignment: Are Multimodal Models Better than Language Models?","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2604.16902","title":"Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2210.09550","title":"Probing Cross-modal Semantics Alignment Capability from the Textual Perspective","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2405.16277","title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2211.04971","title":"Understanding Cross-modal Interactions in V&L Models that Generate Scene Descriptions","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2304.14986","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2405.20846","title":"Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2506.15339","title":"DeVisE: Behavioral Testing of Medical Large Language Models","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2510.26302","title":"Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2309.11252","title":"The Scenario Refiner: Grounding subjects in images at the morphological level","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2401.14212","title":"Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2405.08454","title":"Alignment Helps Make the Most of Multimodal Data","created":"2024-05-14","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":"2510.16322","title":"Memorizing Long-tail Data Can Help Generalization Through Composition","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2511.19470","title":"Quantifying Modality Contributions via Disentangling Multimodal Representations","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2605.06157","title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2608.03631","title":"SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.16396","title":"Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2306.01753","title":"Preconditioned Visual Language Inference with Weak Supervision","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2311.16261","title":"RelVAE: Generative Pretraining for few-shot Visual Relationship Detection","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2409.01389","title":"CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2409.18868","title":"Individuation in Neural Models with and without Visual Grounding","created":"2024-09-27","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":"2602.23906","title":"Half-Truths Break Similarity-Based Retrieval","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2607.03143","title":"Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.13437","title":"CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification","created":"2026-07-15","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":"2609.19767","title":"Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.19812","title":"Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}