{"total":236,"rows":[{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241,"area":null},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"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":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2204.13807","title":"A very preliminary analysis of DALL-E 2","created":"2022-04-25","cited_by_count":82,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"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":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"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":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2406.07546","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","created":"2024-06-11","cited_by_count":52,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48,"area":null},{"id":"2306.01667","title":"Towards In-context Scene Understanding","created":"2023-06-02","cited_by_count":47,"area":null},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","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":"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":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42,"area":null},{"id":"2210.00482","title":"Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language","created":"2022-10-02","cited_by_count":42,"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":"2309.14356","title":"COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs","created":"2023-09-23","cited_by_count":39,"area":null},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"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":"2412.04616","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","created":"2024-12-05","cited_by_count":32,"area":null},{"id":"2505.23493","title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","created":"2025-05-29","cited_by_count":32,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"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":"2211.09935","title":"CAPE: Corrective Actions from Precondition Errors using Large Language Models","created":"2022-11-17","cited_by_count":30,"area":null},{"id":"2306.14636","title":"Localized Text-to-Image Generation for Free via Cross Attention Control","created":"2023-06-26","cited_by_count":27,"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":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","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":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","cited_by_count":25,"area":null},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","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":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24,"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":"2303.15445","title":"IRFL: Image Recognition of Figurative Language","created":"2023-03-27","cited_by_count":23,"area":null},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"id":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","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":"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":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","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":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"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":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","cited_by_count":12,"area":null},{"id":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2403.19103","title":"Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2205.09256","title":"Training Vision-Language Transformers from Captions","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"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":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2402.04492","title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2503.15485","title":"TULIP: Towards Unified Language-Image Pretraining","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2401.05300","title":"I am a Strange Dataset: Metalinguistic Tests for Language Models","created":"2024-01-10","cited_by_count":10,"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":"2407.19474","title":"Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models","created":"2024-07-28","cited_by_count":10,"area":null},{"id":"2506.08210","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","created":"2025-06-09","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":"2311.07766","title":"Vision-Language Integration in Multimodal Video Transformers (Partially) Aligns with the Brain","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2411.17066","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2305.19374","title":"Compositional diversity in visual concept learning","created":"2023-05-30","cited_by_count":8,"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":"2406.10228","title":"VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models","created":"2024-06-14","cited_by_count":8,"area":null}],"next_cursor":"100"}