{"total":91,"rows":[{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418,"area":"mllm"},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080,"area":"mllm"},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565,"area":"mllm"},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224,"area":"mllm"},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712,"area":"mllm"},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704,"area":"mllm"},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692,"area":"mllm"},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563,"area":"mllm"},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550,"area":"mllm"},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509,"area":"mllm"},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357,"area":"mllm"},{"id":"2311.01378","title":"Vision-Language Foundation Models as Effective Robot Imitators","created":"2023-11-02","cited_by_count":349,"area":"mllm"},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2410.17247","title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","created":"2024-10-22","cited_by_count":294,"area":"mllm"},{"id":"2406.18521","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","created":"2024-06-26","cited_by_count":234,"area":"mllm"},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232,"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":"2403.00231","title":"Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models","created":"2024-03-01","cited_by_count":139,"area":"mllm"},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139,"area":"mllm"},{"id":"2402.12451","title":"The Revolution of Multimodal Large Language Models: A Survey","created":"2024-02-19","cited_by_count":137,"area":"mllm"},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2312.16886","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","created":"2023-12-28","cited_by_count":122,"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":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98,"area":"mllm"},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2404.13046","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","created":"2024-04-19","cited_by_count":83,"area":"mllm"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2501.14818","title":"Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models","created":"2025-01-20","cited_by_count":70,"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":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65,"area":"mllm"},{"id":"2403.02325","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","created":"2024-03-04","cited_by_count":64,"area":"mllm"},{"id":"2410.16153","title":"Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages","created":"2024-10-21","cited_by_count":64,"area":"mllm"},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2402.13220","title":"How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts","created":"2024-02-20","cited_by_count":47,"area":"mllm"},{"id":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"id":"2406.05127","title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM","created":"2024-06-07","cited_by_count":45,"area":"mllm"},{"id":"2502.16707","title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation","created":"2025-02-23","cited_by_count":42,"area":"mllm"},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41,"area":"mllm"},{"id":"2504.02477","title":"Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision","created":"2025-04-03","cited_by_count":40,"area":"mllm"},{"id":"2307.01003","title":"Visual Instruction Tuning with Polite Flamingo","created":"2023-07-03","cited_by_count":38,"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":"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":"2412.08746","title":"DocVLM: Make Your VLM an Efficient Reader","created":"2024-12-11","cited_by_count":28,"area":"mllm"},{"id":"2503.15621","title":"LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning","created":"2025-03-19","cited_by_count":28,"area":"mllm"},{"id":"2408.02034","title":"Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid","created":"2024-08-04","cited_by_count":26,"area":"mllm"},{"id":"2407.17453","title":"VILA$^2$: VILA Augmented VILA","created":"2024-07-24","cited_by_count":25,"area":"mllm"},{"id":"2410.08876","title":"RoRA-VLM: Robust Retrieval-Augmented Vision Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"id":"2310.12100","title":"Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling","created":"2023-10-18","cited_by_count":20,"area":"mllm"},{"id":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20,"area":"mllm"},{"id":"2312.05278","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","created":"2023-12-08","cited_by_count":17,"area":"mllm"},{"id":"2508.09945","title":"VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models","created":"2025-08-13","cited_by_count":16,"area":"mllm"},{"id":"2503.02304","title":"A Token-level Text Image Foundation Model for Document Understanding","created":"2025-03-04","cited_by_count":14,"area":"mllm"},{"id":"2407.14506","title":"On Pre-training of Multimodal Language Models Customized for Chart Understanding","created":"2024-07-19","cited_by_count":13,"area":"mllm"},{"id":"2503.19510","title":"RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation","created":"2025-03-25","cited_by_count":12,"area":"mllm"},{"id":"2405.21013","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","created":"2024-05-31","cited_by_count":11,"area":"mllm"},{"id":"2408.02454","title":"VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments","created":"2024-08-05","cited_by_count":11,"area":"mllm"},{"id":"2311.17851","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","created":"2023-11-29","cited_by_count":10,"area":"mllm"},{"id":"2406.00977","title":"Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models","created":"2024-06-03","cited_by_count":8,"area":"mllm"},{"id":"2601.09954","title":"The Spatial Blindspot of Vision-Language Models","created":"2026-01-15","cited_by_count":8,"area":"mllm"},{"id":"2410.09454","title":"Skipping Computations in Multimodal LLMs","created":"2024-10-12","cited_by_count":7,"area":"mllm"},{"id":"2506.18504","title":"Generalizing vision-language models to novel domains: A comprehensive survey","created":"2025-06-23","cited_by_count":7,"area":"mllm"},{"id":"2407.08707","title":"Extracting Training Data from Document-Based VQA Models","created":"2024-07-11","cited_by_count":6,"area":"mllm"},{"id":"2406.05410","title":"ChatSR: Multimodal Large Language Models for Scientific Formula Discovery","created":"2024-06-08","cited_by_count":5,"area":"mllm"},{"id":"2506.13638","title":"DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models","created":"2025-06-16","cited_by_count":5,"area":"mllm"},{"id":"2407.15819","title":"Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight","created":"2024-07-22","cited_by_count":4,"area":"mllm"},{"id":"2505.12884","title":"TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks","created":"2025-05-19","cited_by_count":4,"area":"mllm"},{"id":"2507.07104","title":"Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models","created":"2025-07-09","cited_by_count":4,"area":"mllm"},{"id":"2501.05122","title":"Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model","created":"2025-01-09","cited_by_count":3,"area":"mllm"},{"id":"2505.08910","title":"Behind Maya: Building a Multilingual Vision Language Model","created":"2025-05-13","cited_by_count":3,"area":"mllm"},{"id":"2505.15075","title":"Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs","created":"2025-05-21","cited_by_count":3,"area":"mllm"},{"id":"2505.20503","title":"Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review","created":"2025-05-26","cited_by_count":3,"area":"mllm"},{"id":"2511.21272","title":"Co-Training Vision Language Models for Remote Sensing Multi-task Learning","created":"2025-11-26","cited_by_count":3,"area":"mllm"},{"id":"2602.19058","title":"Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer","created":"2026-02-22","cited_by_count":3,"area":"mllm"},{"id":"2503.04858","title":"SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner","created":"2025-03-06","cited_by_count":2,"area":"mllm"},{"id":"2602.18094","title":"OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models","created":"2026-02-20","cited_by_count":2,"area":"mllm"},{"id":"2509.15704","title":"Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance","created":"2025-09-19","cited_by_count":1,"area":"mllm"},{"id":"2509.22123","title":"Multilingual Vision-Language Models, A Survey","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2510.01009","title":"POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency","created":"2025-10-01","cited_by_count":1,"area":"mllm"},{"id":"2510.18304","title":"The Impact of Image Resolution on Biomedical Multimodal Large Language Models","created":"2025-10-21","cited_by_count":1,"area":"mllm"},{"id":"2602.16138","title":"IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models","created":"2026-02-18","cited_by_count":1,"area":"mllm"},{"id":"2605.30126","title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2506.19579","title":"Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding","created":"2025-06-24","cited_by_count":0,"area":"mllm"},{"id":"2510.09586","title":"Vision Language Models: A Survey of 26K Papers","created":"2025-10-10","cited_by_count":0,"area":"mllm"},{"id":"2603.06141","title":"Spatial Colour Mixing Illusions as a Perception Stress Test for Vision-Language Models","created":"2026-03-06","cited_by_count":0,"area":"mllm"},{"id":"2605.31401","title":"\"\\^{I}n\\c{t}elegi Rom\\^ane\\c{s}te?'' A Recipe for Romanian Vision-Language Models","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.20641","title":"MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2608.20382","title":"Decoupled Vision-Language System for Multimodal Understanding and Generation","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2610.11469","title":"SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}