{"total":114,"rows":[{"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":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2502.17422","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","created":"2025-02-24","cited_by_count":176,"area":"mllm"},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"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":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74,"area":"mllm"},{"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":"2311.15596","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","created":"2023-11-27","cited_by_count":60,"area":"lr"},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"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":"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":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"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":"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":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"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":"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":"2310.00647","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","created":"2023-10-01","cited_by_count":30,"area":"mllm"},{"id":"2504.10514","title":"ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness","created":"2025-04-10","cited_by_count":28,"area":"lr"},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"area":null},{"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":"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":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21,"area":"mllm"},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","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":"2312.15043","title":"GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection","created":"2023-12-22","cited_by_count":20,"area":"mllm"},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","cited_by_count":19,"area":"mllm"},{"id":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17,"area":"mllm"},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","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":"2308.13177","title":"How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection","created":"2023-08-25","cited_by_count":15,"area":"mllm"},{"id":"2310.16033","title":"Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs","created":"2023-10-24","cited_by_count":15,"area":"mllm"},{"id":"2305.10722","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","created":"2023-05-18","cited_by_count":14,"area":"diffusion"},{"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":"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":"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":"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":"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":"2304.12539","title":"Text-guided Eyeglasses Manipulation with Spatial Constraints","created":"2023-04-25","cited_by_count":10,"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":"2406.09121","title":"MMRel: Benchmarking Relation Understanding in Multi-Modal Large Language Models","created":"2024-06-13","cited_by_count":10,"area":"mllm"},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"id":"2406.14137","title":"MACAROON: Training Vision-Language Models To Be Your Engaged Partners","created":"2024-06-20","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":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"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":"2510.08919","title":"PHyCLIP: $\\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning","created":"2025-10-10","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":"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":"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":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2310.13473","title":"Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language Models","created":"2023-10-20","cited_by_count":5,"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":"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":"2505.20021","title":"Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models","created":"2025-05-26","cited_by_count":4,"area":"lr"},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","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":"2412.08111","title":"Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models","created":"2024-12-11","cited_by_count":3,"area":"mllm"},{"id":"2412.13947","title":"Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition","created":"2024-12-18","cited_by_count":3,"area":"mllm"},{"id":"2503.23062","title":"Shape and Texture Recognition in Large Vision-Language Models","created":"2025-03-29","cited_by_count":3,"area":"mllm"},{"id":"2305.18786","title":"Scalable Performance Analysis for Vision-Language Models","created":"2023-05-30","cited_by_count":2,"area":"mllm"},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2407.21001","title":"GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models","created":"2024-07-30","cited_by_count":2,"area":"mllm"},{"id":"2507.04699","title":"A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets","created":"2025-07-07","cited_by_count":2,"area":"lr"},{"id":"2512.17178","title":"ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2512.21150","title":"ORCA: Object Recognition and Comprehension for Archiving Marine Species","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2603.12266","title":"MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"id":"2607.23052","title":"Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models","created":"2026-07-25","cited_by_count":2,"area":"mllm"},{"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":"2408.09511","title":"NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2408.13898","title":"Evaluating Attribute Comprehension in Large Vision-Language Models","created":"2024-08-25","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":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.07196","title":"SAP-Bench: Benchmarking Multimodal Large Language Models in Surgical Action Planning","created":"2025-06-08","cited_by_count":1,"area":"mllm"},{"id":"2506.16724","title":"The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models","created":"2025-06-20","cited_by_count":1,"area":"mllm"},{"id":"2509.06105","title":"PathoHR: Hierarchical Reasoning for Vision-Language Models in Pathology","created":"2025-09-07","cited_by_count":1,"area":"lr"},{"id":"2509.13676","title":"Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation","created":"2025-09-17","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":"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":"2602.23351","title":"Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"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":"2607.12290","title":"The Sound of Absence: Audio-Language Embedding Models Struggle with Negation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2609.08242","title":"CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning","created":"2026-09-08","cited_by_count":1,"area":"lr"},{"id":"2412.08125","title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models","created":"2024-12-11","cited_by_count":0,"area":"lr"},{"id":"2503.13021","title":"Dynamic Relation Inference via Verb Embeddings","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2506.00869","title":"What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning","created":"2025-06-01","cited_by_count":0,"area":"lr"},{"id":"2603.06600","title":"FuzzingRL: Reinforcement Fuzz-Testing for Revealing VLM Failures","created":"2026-02-17","cited_by_count":0,"area":"mllm"},{"id":"2603.23867","title":"Can VLMs Reason Robustly? A Neuro-Symbolic Investigation","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2604.12335","title":"SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}