{"total":109,"rows":[{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529,"area":"lr"},{"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":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236,"area":"diffusion"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"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":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114,"area":"mllm"},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86,"area":"mllm"},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72,"area":null},{"id":"2411.18620","title":"Cross-modal Information Flow in Multimodal Large Language Models","created":"2024-11-27","cited_by_count":67,"area":"mllm"},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2306.01667","title":"Towards In-context Scene Understanding","created":"2023-06-02","cited_by_count":47,"area":null},{"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":"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":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2403.00742","title":"Dialect prejudice predicts AI decisions about people's character, employability, and criminality","created":"2024-03-01","cited_by_count":37,"area":null},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2303.00040","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","created":"2023-02-28","cited_by_count":32,"area":null},{"id":"2305.13812","title":"Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality","created":"2023-05-23","cited_by_count":32,"area":"mllm"},{"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":"2410.09733","title":"MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models","created":"2024-10-13","cited_by_count":31,"area":"mllm"},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"area":"mllm"},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"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":"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":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"area":null},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21,"area":"mllm"},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2311.13833","title":"Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models","created":"2023-11-23","cited_by_count":19,"area":"diffusion"},{"id":"2308.09778","title":"Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models","created":"2023-08-18","cited_by_count":18,"area":"lr"},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","cited_by_count":17,"area":"mllm"},{"id":"2405.09931","title":"Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","created":"2024-05-16","cited_by_count":17,"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":"2312.00096","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","created":"2023-11-30","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":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"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":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13,"area":"mllm"},{"id":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2403.14760","title":"Can 3D Vision-Language Models Truly Understand Natural Language?","created":"2024-03-21","cited_by_count":12,"area":"mllm"},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"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":"2312.04231","title":"Adventures of Trustworthy Vision-Language Models: A Survey","created":"2023-12-07","cited_by_count":10,"area":"mllm"},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2109.07301","title":"What Vision-Language Models `See' when they See Scenes","created":"2021-09-15","cited_by_count":8,"area":"mllm"},{"id":"2210.12079","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"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":"2406.09240","title":"Comparison Visual Instruction Tuning","created":"2024-06-13","cited_by_count":8,"area":"lr"},{"id":"2509.14837","title":"V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models","created":"2025-09-18","cited_by_count":8,"area":"mllm"},{"id":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"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":"2305.14307","title":"Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models","created":"2023-05-23","cited_by_count":7,"area":null},{"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":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6,"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":"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":"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":"2506.02803","title":"SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking","created":"2025-06-03","cited_by_count":6,"area":"lr"},{"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":"2306.16533","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","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":"2508.15360","title":"An Empirical Study on How Video-LLMs Answer Video Questions","created":"2025-08-21","cited_by_count":4,"area":null},{"id":"2404.19128","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM","created":"2024-04-29","cited_by_count":3,"area":"mllm"},{"id":"2409.06579","title":"Quantifying and Enabling the Interpretability of CLIP-like Models","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2410.24219","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2509.21287","title":"DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding","created":"2025-09-25","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":"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":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","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":"2408.06622","title":"ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2510.17247","title":"From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models","created":"2025-10-20","cited_by_count":2,"area":"diffusion"},{"id":"2305.03517","title":"Few-shot Domain-Adaptive Visually-fused Event Detection from Text","created":"2023-05-04","cited_by_count":1,"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":"2401.16575","title":"Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2409.08206","title":"ComAlign: Compositional Alignment in Vision-Language Models","created":"2024-09-12","cited_by_count":1,"area":"mllm"},{"id":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2411.05023","title":"Multimodal Quantum Natural Language Processing: A Novel Framework for using Quantum Methods to Analyse Real Data","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2411.15628","title":"ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos","created":"2024-11-23","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":"2503.11103","title":"Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2505.02278","title":"Compositional Image-Text Matching and Retrieval by Grounding Entities","created":"2025-05-04","cited_by_count":1,"area":"mllm"},{"id":"2509.03025","title":"Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens","created":"2025-09-03","cited_by_count":1,"area":"mllm"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"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}],"next_cursor":"100"}