{"total":135,"rows":[{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293,"area":"lr"},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254,"area":"lr"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"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":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"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":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41,"area":"mllm"},{"id":"2403.18346","title":"Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective","created":"2024-03-27","cited_by_count":39,"area":"mllm"},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2505.17127","title":"Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts","created":"2025-05-21","cited_by_count":32,"area":"mllm"},{"id":"2410.14398","title":"Dynamic Negative Guidance of Diffusion Models","created":"2024-10-18","cited_by_count":28,"area":"diffusion"},{"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":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2504.01916","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","created":"2025-04-02","cited_by_count":23,"area":"mllm"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"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":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17,"area":"mllm"},{"id":"2404.14715","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","created":"2024-04-23","cited_by_count":17,"area":"mllm"},{"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":"2401.17981","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","created":"2024-01-31","cited_by_count":16,"area":"mllm"},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"area":"mllm"},{"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":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"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":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11,"area":"mllm"},{"id":"2308.03151","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","created":"2023-08-06","cited_by_count":10,"area":"mllm"},{"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":"2406.19131","title":"CELLO: Causal Evaluation of Large Vision-Language Models","created":"2024-06-27","cited_by_count":10,"area":"lr"},{"id":"2503.01891","title":"MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems","created":"2025-02-27","cited_by_count":10,"area":"lr"},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2310.08577","title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2504.16801","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","created":"2025-04-23","cited_by_count":9,"area":"distill"},{"id":"2606.18943","title":"Physics-IQ Verified","created":"2026-06-17","cited_by_count":9,"area":"wm"},{"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":"2407.01081","title":"CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation","created":"2024-07-01","cited_by_count":8,"area":"mllm"},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"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":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"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":"2505.18434","title":"TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP","created":"2025-05-24","cited_by_count":7,"area":"mllm"},{"id":"2209.06103","title":"VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models","created":"2022-09-12","cited_by_count":6,"area":"mllm"},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2308.10509","title":"An Examination of the Compositionality of Large Generative Vision-Language Models","created":"2023-08-21","cited_by_count":6,"area":"mllm"},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6,"area":"mllm"},{"id":"2310.02777","title":"The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models","created":"2023-10-04","cited_by_count":6,"area":"mllm"},{"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":"2503.23137","title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","created":"2025-03-29","cited_by_count":5,"area":"lr"},{"id":"2505.24424","title":"Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":5,"area":"mllm"},{"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":"2408.01959","title":"Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI","created":"2024-08-04","cited_by_count":4,"area":"diffusion"},{"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":"2601.03500","title":"SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models","created":"2026-01-07","cited_by_count":3,"area":"mllm"},{"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":"2305.18786","title":"Scalable Performance Analysis for Vision-Language Models","created":"2023-05-30","cited_by_count":2,"area":"mllm"},{"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":"2407.17914","title":"Vision-Language Models Align with Human Neural Representations in Concept Processing","created":"2024-07-25","cited_by_count":2,"area":"mllm"},{"id":"2505.15576","title":"Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models","created":"2025-05-21","cited_by_count":2,"area":"lr"},{"id":"2506.15339","title":"DeVisE: Behavioral Testing of Medical Large Language Models","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2510.16540","title":"Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"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":"2412.04429","title":"Grounding Descriptions in Images informs Zero-Shot Visual Recognition","created":"2024-12-05","cited_by_count":1,"area":"mllm"},{"id":"2501.11469","title":"MASS: Overcoming Language Bias in Image-Text Matching","created":"2025-01-20","cited_by_count":1,"area":"mllm"},{"id":"2507.09615","title":"Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score","created":"2025-07-13","cited_by_count":1,"area":"mllm"},{"id":"2507.13405","title":"COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark","created":"2025-07-17","cited_by_count":1,"area":"lr"},{"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":"2606.13288","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","created":"2026-06-11","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}