{"total":208,"rows":[{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"area":"mllm"},{"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":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388,"area":"mllm"},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316,"area":"mllm"},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"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":"2312.12856","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","created":"2023-12-20","cited_by_count":125,"area":"mllm"},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119,"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":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101,"area":"mllm"},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74,"area":"mllm"},{"id":"2504.17432","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","created":"2025-04-24","cited_by_count":73,"area":"mllm"},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","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":"2501.04931","title":"Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency","created":"2025-01-09","cited_by_count":51,"area":"mllm"},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46,"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":"2410.10855","title":"Core Knowledge Deficits in Multi-Modal Language Models","created":"2024-10-06","cited_by_count":38,"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":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"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":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30,"area":"mllm"},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"area":"mllm"},{"id":"2504.10462","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","created":"2025-04-14","cited_by_count":30,"area":"mllm"},{"id":"2401.17221","title":"MouSi: Poly-Visual-Expert Vision-Language Models","created":"2024-01-30","cited_by_count":24,"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":"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":"2404.06510","title":"Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?","created":"2024-04-09","cited_by_count":20,"area":"mllm"},{"id":"2412.15484","title":"Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage","created":"2024-12-20","cited_by_count":20,"area":"mllm"},{"id":"2406.09250","title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","created":"2024-06-13","cited_by_count":19,"area":"mllm"},{"id":"2409.19967","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","created":"2024-09-30","cited_by_count":19,"area":"mllm"},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","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":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17,"area":"mllm"},{"id":"2308.01313","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","created":"2023-08-02","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":"2312.04533","title":"Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models","created":"2023-12-07","cited_by_count":16,"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":"2412.13652","title":"RelationField: Relate Anything in Radiance Fields","created":"2024-12-18","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":"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":"2412.06474","title":"Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding","created":"2024-12-09","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":"2306.16048","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":"2402.17510","title":"Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning","created":"2024-02-27","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":"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":"2405.08815","title":"Efficient Vision-Language Pre-training by Cluster Masking","created":"2024-05-14","cited_by_count":13,"area":"mllm"},{"id":"2412.08737","title":"Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions","created":"2024-12-11","cited_by_count":13,"area":"mllm"},{"id":"2506.15871","title":"Visual symbolic mechanisms: Emergent symbol processing in vision language models","created":"2025-06-18","cited_by_count":13,"area":"mllm"},{"id":"2307.15460","title":"Cross-Modal Concept Learning and Inference for Vision-Language Models","created":"2023-07-28","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":"2312.06112","title":"MAFA: Managing False Negatives for Vision-Language Pre-training","created":"2023-12-11","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":"2504.05457","title":"Taxonomy-Aware Evaluation of Vision-Language Models","created":"2025-04-07","cited_by_count":11,"area":"mllm"},{"id":"2507.22431","title":"HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models","created":"2025-07-30","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":"2406.09121","title":"MMRel: Benchmarking Relation Understanding in Multi-Modal Large Language Models","created":"2024-06-13","cited_by_count":10,"area":"mllm"},{"id":"2409.18286","title":"Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing","created":"2024-09-26","cited_by_count":10,"area":"mllm"},{"id":"2507.21391","title":"Multimodal LLMs as Customized Reward Models for Text-to-Image Generation","created":"2025-07-28","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":"2402.02103","title":"D\\'ej\\`a Vu Memorization in Vision-Language Models","created":"2024-02-03","cited_by_count":9,"area":"mllm"},{"id":"2503.11005","title":"Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection","created":"2025-03-14","cited_by_count":9,"area":"mllm"},{"id":"2402.15300","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","created":"2024-02-23","cited_by_count":8,"area":"mllm"},{"id":"2402.16315","title":"Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models","created":"2024-02-26","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":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8,"area":"mllm"},{"id":"2304.10727","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","created":"2023-04-21","cited_by_count":7,"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":"2408.05478","title":"Multi-Agent Planning Using Visual Language Models","created":"2024-08-10","cited_by_count":7,"area":"mllm"},{"id":"2501.01371","title":"CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering","created":"2025-01-02","cited_by_count":7,"area":"mllm"},{"id":"2502.08317","title":"Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting","created":"2025-02-12","cited_by_count":7,"area":"mllm"},{"id":"2504.09456","title":"Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs","created":"2025-04-13","cited_by_count":7,"area":"mllm"},{"id":"2505.18434","title":"TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP","created":"2025-05-24","cited_by_count":7,"area":"mllm"},{"id":"2508.11317","title":"Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models","created":"2025-08-15","cited_by_count":7,"area":"mllm"},{"id":"2508.11330","title":"Noise Matters: Optimizing Matching Noise for Diffusion Classifiers","created":"2025-08-15","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":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2502.15210","title":"PairBench: Are Vision-Language Models Reliable at Comparing What They See?","created":"2025-02-21","cited_by_count":6,"area":"mllm"},{"id":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"area":"mllm"},{"id":"2407.15239","title":"Benchmark Granularity and Model Robustness for Image-Text Retrieval","created":"2024-07-21","cited_by_count":5,"area":"mllm"},{"id":"2408.05334","title":"Revisiting Multi-Modal LLM Evaluation","created":"2024-08-09","cited_by_count":5,"area":"mllm"},{"id":"2412.18404","title":"Extract Free Dense Misalignment from CLIP","created":"2024-12-24","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":"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"}],"next_cursor":"100"}