{"total":84,"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":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"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":"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":"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":"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":"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":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"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":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"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":"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":"2305.14428","title":"Prompting Language-Informed Distribution for Compositional Zero-Shot Learning","created":"2023-05-23","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":"2311.03354","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","created":"2023-11-06","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":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","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":"2310.16494","title":"Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction","created":"2023-10-25","cited_by_count":19,"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":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"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":"2406.08787","title":"A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices","created":"2024-06-13","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":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2407.05897","title":"Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models","created":"2024-07-08","cited_by_count":13,"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":"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":"2402.11414","title":"Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization","created":"2024-02-18","cited_by_count":10,"area":null},{"id":"2505.22079","title":"Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2403.02626","title":"Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use","created":"2024-03-05","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":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2510.01685","title":"How Do Language Models Compose Functions?","created":"2025-10-02","cited_by_count":8,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","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":"2406.09952","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2502.05432","title":"MoFM: A Large-Scale Human Motion Foundation Model","created":"2025-02-08","cited_by_count":5,"area":null},{"id":"2506.04461","title":"Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey","created":"2025-06-04","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":"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":"2410.05869","title":"Believing is Seeing: Unobserved Object Detection using Generative Models","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2410.10291","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2502.19828","title":"Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2407.05118","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","created":"2024-07-06","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":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2309.04504","title":"Compositional Learning of Visually-Grounded Concepts Using Reinforcement","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2311.01580","title":"MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2311.14837","title":"Benchmarking Robustness of Text-Image Composed Retrieval","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2406.07699","title":"CUPID: Contextual Understanding of Prompt-conditioned Image Distributions","created":"2024-06-11","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":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","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":"2305.16328","title":"Semantic Composition in Visually Grounded Language Models","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2404.12013","title":"Sequential Compositional Generalization in Multimodal Models","created":"2024-04-18","cited_by_count":1,"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":"2408.09269","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2505.24211","title":"Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2508.00085","title":"Punching Bag vs. Punching Person: Motion Transferability in Videos","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2509.17641","title":"AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2511.03001","title":"Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.08854","title":"Is Generation Required for Data-Efficient Perception?","created":"2025-12-09","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":"2409.00973","title":"IVGF: The Fusion-Guided Infrared and Visible General Framework","created":"2024-09-02","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":"2410.15866","title":"Visual Motif Identification: Elaboration of a Curated Comparative Dataset and Classification Methods","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2412.12877","title":"PRIMEdit: Probability Redistribution for Instance-Aware Multi-Object Video Editing With a New Benchmark Dataset","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2505.17096","title":"TAGS: 3D Tumor-Adaptive Guidance for SAM","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2508.21795","title":"TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2602.16689","title":"Are Object-Centric Representations Better At Compositional Generalization?","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.12606","title":"Mastering Negation: Boosting Grounding Models via Grouped Opposition-Based Learning","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.31503","title":"How can embedding models bind concepts?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.07135","title":"Sparse Attention for Dense Open-Vocabulary Prediction in CLIP","created":"2026-07-08","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":"2608.29604","title":"RePair: Turning Retrieval Failures into Counterfactual Hard Pairs","created":"2026-08-30","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":"2610.15035","title":"What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training Strategies","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}