{"total":72,"rows":[{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"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":"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":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50,"area":"mllm"},{"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":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2402.13254","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","created":"2024-02-20","cited_by_count":35,"area":"lr"},{"id":"2311.03964","title":"Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining","created":"2023-11-07","cited_by_count":25,"area":"lr"},{"id":"2403.12736","title":"Towards Multimodal In-Context Learning for Vision & Language Models","created":"2024-03-19","cited_by_count":25,"area":"mllm"},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"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":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22,"area":"alignment"},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2406.08164","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","created":"2024-06-12","cited_by_count":21,"area":"lr"},{"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":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19,"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":"2404.05016","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","created":"2024-04-07","cited_by_count":12,"area":null},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2510.06783","title":"TTRV: Test-Time Reinforcement Learning for Vision Language Models","created":"2025-10-08","cited_by_count":10,"area":"mllm"},{"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":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2407.17827","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","created":"2024-07-25","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":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2410.06154","title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models","created":"2024-10-08","cited_by_count":6,"area":"mllm"},{"id":"2411.08753","title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","created":"2024-11-13","cited_by_count":6,"area":null},{"id":"2411.13317","title":"Teaching VLMs to Localize Specific Objects from In-context Examples","created":"2024-11-20","cited_by_count":6,"area":"mllm"},{"id":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2412.19920","title":"Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models","created":"2024-12-27","cited_by_count":5,"area":null},{"id":"2505.24424","title":"Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":5,"area":"mllm"},{"id":"2508.02329","title":"VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions","created":"2025-08-04","cited_by_count":5,"area":"mllm"},{"id":"2509.24566","title":"TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models","created":"2025-09-29","cited_by_count":5,"area":"mllm"},{"id":"2502.15370","title":"Weakly Supervised Video Scene Graph Generation via Natural Language Supervision","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2507.07985","title":"Common Data Properties Limit Object-Attribute Binding in CLIP","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2405.15684","title":"Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models","created":"2024-05-24","cited_by_count":3,"area":"mllm"},{"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":"2411.19106","title":"Detailed Object Description with Controllable Dimensions","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2602.05729","title":"Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification","created":"2026-02-05","cited_by_count":3,"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":"2504.04740","title":"SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data","created":"2025-04-07","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":"2505.20152","title":"MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models","created":"2025-05-26","cited_by_count":2,"area":"mllm"},{"id":"2506.08194","title":"GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra","created":"2025-06-09","cited_by_count":2,"area":"lr"},{"id":"2509.03897","title":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","created":"2025-09-04","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":"2407.15487","title":"In-Context Learning Improves Compositional Understanding of Vision-Language Models","created":"2024-07-22","cited_by_count":1,"area":"mllm"},{"id":"2408.09511","title":"NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2412.07161","title":"Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2504.14359","title":"A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language Modeling","created":"2025-04-19","cited_by_count":1,"area":"mllm"},{"id":"2511.12452","title":"DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions","created":"2025-11-16","cited_by_count":1,"area":"mllm"},{"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"},{"id":"2607.23271","title":"What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2608.30194","title":"NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation","created":"2026-08-31","cited_by_count":1,"area":"diffusion"},{"id":"2503.13021","title":"Dynamic Relation Inference via Verb Embeddings","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2509.24192","title":"Talk in Pieces, See in Whole: Disentangled and Hierarchical Representation Learning in Language-based Object Detection","created":"2025-09-29","cited_by_count":0,"area":"mllm"},{"id":"2602.23906","title":"Half-Truths Break Similarity-Based Retrieval","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.25722","title":"No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.12335","title":"SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2605.22651","title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2607.10796","title":"Mixture of Cognitive Experts in Large Vision-Language Models","created":"2026-07-12","cited_by_count":0,"area":"lr"},{"id":"2608.15971","title":"The Limits of Binding in Dual Encoders","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.31456","title":"Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}