{"total":216,"rows":[{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719,"area":"mllm"},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906,"area":"mllm"},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"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":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"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":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2411.16537","title":"RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics","created":"2024-11-25","cited_by_count":136,"area":"mllm"},{"id":"2402.05935","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","created":"2024-02-08","cited_by_count":131,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2408.08872","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","created":"2024-08-16","cited_by_count":116,"area":"mllm"},{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102,"area":"mllm"},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93,"area":"mllm"},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"id":"2310.05338","title":"Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models","created":"2023-10-09","cited_by_count":80,"area":"mllm"},{"id":"2401.02384","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","created":"2024-01-04","cited_by_count":79,"area":"mllm"},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2204.03574","title":"Learning to Compose Soft Prompts for Compositional Zero-Shot Learning","created":"2022-04-07","cited_by_count":67,"area":"mllm"},{"id":"2406.20076","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","created":"2024-06-28","cited_by_count":65,"area":"mllm"},{"id":"2502.09696","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","created":"2025-02-13","cited_by_count":58,"area":"mllm"},{"id":"2502.14846","title":"Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation","created":"2025-02-20","cited_by_count":58,"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":"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":"2505.17015","title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","created":"2025-05-22","cited_by_count":52,"area":"mllm"},{"id":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"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":"2312.08366","title":"See, Say, and Segment: Teaching LMMs to Overcome False Premises","created":"2023-12-13","cited_by_count":41,"area":"mllm"},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2410.08145","title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs","created":"2024-10-10","cited_by_count":38,"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":"2509.25541","title":"Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play","created":"2025-09-29","cited_by_count":37,"area":"mllm"},{"id":"2308.03793","title":"ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation","created":"2023-08-04","cited_by_count":35,"area":"mllm"},{"id":"2503.10582","title":"VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search","created":"2025-03-13","cited_by_count":35,"area":"mllm"},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"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":"2410.00193","title":"Do Vision-Language Models Really Understand Visual Language?","created":"2024-09-30","cited_by_count":32,"area":"mllm"},{"id":"2311.14552","title":"Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models","created":"2023-11-24","cited_by_count":31,"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":"2412.12693","title":"SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation","created":"2024-12-17","cited_by_count":31,"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":"2403.09333","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","created":"2024-03-14","cited_by_count":29,"area":"mllm"},{"id":"2311.09048","title":"GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models","created":"2023-11-15","cited_by_count":28,"area":"mllm"},{"id":"2412.09616","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","created":"2024-12-12","cited_by_count":28,"area":"mllm"},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2407.17453","title":"VILA$^2$: VILA Augmented VILA","created":"2024-07-24","cited_by_count":25,"area":"mllm"},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2504.21447","title":"Multimodal Language Models See Better When They Look Shallower","created":"2025-04-30","cited_by_count":23,"area":"mllm"},{"id":"2506.05453","title":"MLLM-CL: Continual Learning for Multimodal Large Language Models","created":"2025-06-05","cited_by_count":23,"area":"mllm"},{"id":"2501.05901","title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","created":"2025-01-10","cited_by_count":21,"area":"mllm"},{"id":"2505.19015","title":"Can Multimodal Large Language Models Understand Spatial Relations?","created":"2025-05-25","cited_by_count":20,"area":"mllm"},{"id":"2501.09167","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA","created":"2025-01-15","cited_by_count":19,"area":"mllm"},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"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":"2503.12127","title":"Hyperbolic Safety-Aware Vision-Language Models","created":"2025-03-15","cited_by_count":17,"area":"mllm"},{"id":"2509.24791","title":"Vision Function Layer in Multimodal LLMs","created":"2025-09-29","cited_by_count":17,"area":"mllm"},{"id":"2410.18857","title":"Probabilistic Language-Image Pre-Training","created":"2024-10-24","cited_by_count":16,"area":"mllm"},{"id":"2404.11207","title":"Exploring the Transferability of Visual Prompting for Multimodal Large Language Models","created":"2024-04-17","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":"2406.07236","title":"Let Go of Your Labels with Unsupervised Transfer","created":"2024-06-11","cited_by_count":14,"area":"mllm"},{"id":"2509.14033","title":"SAIL-VL2 Technical Report","created":"2025-09-17","cited_by_count":14,"area":"mllm"},{"id":"2311.17091","title":"Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models","created":"2023-11-28","cited_by_count":13,"area":"mllm"},{"id":"2404.02415","title":"What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases","created":"2024-04-03","cited_by_count":13,"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":"2306.08893","title":"LOVM: Language-Only Vision Model Selection","created":"2023-06-15","cited_by_count":12,"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":"2502.17297","title":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","created":"2025-02-24","cited_by_count":12,"area":"mllm"},{"id":"2503.21817","title":"Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping","created":"2025-03-26","cited_by_count":12,"area":"mllm"},{"id":"2508.04650","title":"EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts","created":"2025-08-06","cited_by_count":12,"area":"mllm"},{"id":"2205.15237","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","created":"2022-05-30","cited_by_count":11,"area":"mllm"},{"id":"2407.04923","title":"OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding","created":"2024-07-06","cited_by_count":11,"area":"mllm"},{"id":"2412.05983","title":"Chimera: Improving Generalist Model with Domain-Specific Experts","created":"2024-12-08","cited_by_count":11,"area":"mllm"},{"id":"2412.16158","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","created":"2024-12-20","cited_by_count":10,"area":"mllm"},{"id":"2504.01328","title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models","created":"2025-04-02","cited_by_count":10,"area":"mllm"},{"id":"2510.04560","title":"ContextNav: Towards Agentic Multimodal In-Context Learning","created":"2025-10-06","cited_by_count":10,"area":"mllm"},{"id":"2510.20229","title":"Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context","created":"2025-10-23","cited_by_count":10,"area":"mllm"},{"id":"2310.08166","title":"Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2503.20502","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning","created":"2025-03-26","cited_by_count":9,"area":"mllm"},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","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":"2409.14993","title":"Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the Unification","created":"2024-09-23","cited_by_count":8,"area":"mllm"},{"id":"2410.02080","title":"EMMA: Efficient Visual Alignment in Multi-Modal LLMs","created":"2024-10-02","cited_by_count":8,"area":"mllm"},{"id":"2412.05243","title":"CompCap: Improving Multimodal Large Language Models with Composite Captions","created":"2024-12-06","cited_by_count":8,"area":"mllm"},{"id":"2502.18816","title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","created":"2025-02-26","cited_by_count":8,"area":"mllm"},{"id":"2510.22535","title":"OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models","created":"2025-10-26","cited_by_count":8,"area":"mllm"},{"id":"2602.01990","title":"SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning","created":"2026-02-02","cited_by_count":8,"area":"mllm"},{"id":"2603.27064","title":"ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding","created":"2026-03-28","cited_by_count":8,"area":"mllm"},{"id":"2504.13199","title":"Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks","created":"2025-04-14","cited_by_count":7,"area":"mllm"},{"id":"2505.17726","title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2510.12750","title":"VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage","created":"2025-10-14","cited_by_count":7,"area":"mllm"},{"id":"2511.12738","title":"Direct Visual Grounding by Directing Attention of Visual Tokens","created":"2025-11-16","cited_by_count":7,"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":"2401.17862","title":"Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis","created":"2024-01-31","cited_by_count":6,"area":"mllm"}],"next_cursor":"100"}