{"total":196,"rows":[{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735,"area":"mllm"},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2309.07915","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","created":"2023-09-14","cited_by_count":172,"area":"mllm"},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97,"area":"mllm"},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2210.09996","title":"Perceptual Grouping in Contrastive Vision-Language Models","created":"2022-10-18","cited_by_count":82,"area":"mllm"},{"id":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69,"area":"mllm"},{"id":"2402.12058","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","created":"2024-02-19","cited_by_count":57,"area":"mllm"},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2306.12424","title":"VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution","created":"2023-06-21","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":"2405.16919","title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models","created":"2024-05-27","cited_by_count":43,"area":"mllm"},{"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":"2305.06152","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","created":"2023-05-06","cited_by_count":37,"area":"mllm"},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36,"area":"mllm"},{"id":"2305.14897","title":"Text encoders bottleneck compositionality in contrastive vision-language models","created":"2023-05-24","cited_by_count":34,"area":"mllm"},{"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":"2406.14544","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","created":"2024-06-20","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":"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":"2511.04655","title":"Benchmark Designers Should \"Train on the Test Set\" to Expose Exploitable Non-Visual Shortcuts","created":"2025-11-06","cited_by_count":29,"area":"mllm"},{"id":"2401.17221","title":"MouSi: Poly-Visual-Expert Vision-Language Models","created":"2024-01-30","cited_by_count":24,"area":"mllm"},{"id":"2212.12043","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models","created":"2022-12-22","cited_by_count":23,"area":"mllm"},{"id":"2312.05291","title":"GlitchBench: Can large multimodal models detect video game glitches?","created":"2023-12-08","cited_by_count":23,"area":"mllm"},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2409.15477","title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","created":"2024-09-23","cited_by_count":23,"area":"mllm"},{"id":"2504.01916","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","created":"2025-04-02","cited_by_count":23,"area":"mllm"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2510.11693","title":"Scaling Language-Centric Omnimodal Representation Learning","created":"2025-10-13","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":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","cited_by_count":20,"area":"mllm"},{"id":"2406.16562","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","created":"2024-06-24","cited_by_count":20,"area":"mllm"},{"id":"2505.20612","title":"Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models","created":"2025-05-27","cited_by_count":20,"area":"mllm"},{"id":"2501.02135","title":"AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs","created":"2025-01-03","cited_by_count":19,"area":"mllm"},{"id":"2411.10979","title":"VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?","created":"2024-11-17","cited_by_count":18,"area":"mllm"},{"id":"2212.10549","title":"Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment","created":"2022-12-20","cited_by_count":17,"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":"2404.12652","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","created":"2024-04-19","cited_by_count":16,"area":"mllm"},{"id":"2409.12969","title":"Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models","created":"2024-09-02","cited_by_count":15,"area":"mllm"},{"id":"2410.04734","title":"TLDR: Token-Level Detective Reward Model for Large Vision Language Models","created":"2024-10-07","cited_by_count":15,"area":"mllm"},{"id":"2411.00304","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","created":"2024-11-01","cited_by_count":15,"area":"mllm"},{"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":"2412.04378","title":"VladVA: Discriminative Fine-tuning of LVLMs","created":"2024-12-05","cited_by_count":15,"area":"mllm"},{"id":"2506.02557","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","created":"2025-06-03","cited_by_count":15,"area":"mllm"},{"id":"2306.09996","title":"Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering","created":"2023-06-16","cited_by_count":14,"area":"mllm"},{"id":"2306.16048","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity","created":"2023-06-28","cited_by_count":14,"area":"mllm"},{"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":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2406.10215","title":"DevBench: A multimodal developmental benchmark for language learning","created":"2024-06-14","cited_by_count":13,"area":"mllm"},{"id":"2412.02368","title":"ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?","created":"2024-12-03","cited_by_count":13,"area":"mllm"},{"id":"2310.02569","title":"ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks","created":"2023-10-04","cited_by_count":12,"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":"2311.05746","title":"Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models","created":"2023-11-09","cited_by_count":11,"area":"mllm"},{"id":"2405.19088","title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","created":"2024-05-29","cited_by_count":11,"area":"mllm"},{"id":"2412.00142","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","created":"2024-11-28","cited_by_count":11,"area":"mllm"},{"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":"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":"2312.06685","title":"Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models","created":"2023-12-09","cited_by_count":10,"area":"mllm"},{"id":"2508.12687","title":"EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding","created":"2025-08-18","cited_by_count":10,"area":"mllm"},{"id":"2211.12402","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","created":"2022-11-22","cited_by_count":9,"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":"2501.19164","title":"Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs","created":"2025-01-31","cited_by_count":9,"area":"mllm"},{"id":"2510.02292","title":"From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens","created":"2025-10-02","cited_by_count":9,"area":"mllm"},{"id":"2408.11748","title":"Understanding Depth and Height Perception in Large Visual-Language Models","created":"2024-08-21","cited_by_count":8,"area":"mllm"},{"id":"2412.03565","title":"INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning","created":"2024-12-04","cited_by_count":8,"area":"mllm"},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2407.07840","title":"Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison","created":"2024-07-10","cited_by_count":7,"area":"mllm"},{"id":"2503.12663","title":"Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding","created":"2025-03-16","cited_by_count":7,"area":"mllm"},{"id":"2607.03647","title":"Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs","created":"2026-07-04","cited_by_count":7,"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":"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":"2311.11477","title":"What's left can't be right -- The remaining positional incompetence of contrastive vision-language models","created":"2023-11-20","cited_by_count":6,"area":"mllm"},{"id":"2409.18023","title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","created":"2024-09-26","cited_by_count":6,"area":"mllm"},{"id":"2410.10112","title":"Can We Predict Performance of Large Models across Vision-Language Tasks?","created":"2024-10-14","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":"2408.05334","title":"Revisiting Multi-Modal LLM Evaluation","created":"2024-08-09","cited_by_count":5,"area":"mllm"},{"id":"2410.02613","title":"NL-Eye: Abductive NLI for Images","created":"2024-10-03","cited_by_count":5,"area":"mllm"},{"id":"2504.01589","title":"Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models","created":"2025-04-02","cited_by_count":5,"area":"mllm"},{"id":"2505.13180","title":"ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models","created":"2025-05-19","cited_by_count":5,"area":"mllm"},{"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":"2511.20515","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"id":"2602.21035","title":"Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuning","created":"2026-02-24","cited_by_count":5,"area":"mllm"},{"id":"2606.00959","title":"Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition","created":"2026-05-31","cited_by_count":5,"area":"mllm"},{"id":"2409.15125","title":"Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation","created":"2024-09-23","cited_by_count":4,"area":"mllm"},{"id":"2506.05146","title":"CIVET: Systematic Evaluation of Understanding in VLMs","created":"2025-06-05","cited_by_count":4,"area":"mllm"}],"next_cursor":"100"}