{"total":117,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869,"area":null},{"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071,"area":"mllm"},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305,"area":"mllm"},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239,"area":"mllm"},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706,"area":"lr"},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446,"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":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308,"area":"mllm"},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193,"area":"mllm"},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164,"area":null},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"area":"mllm"},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2311.10081","title":"DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback","created":"2023-11-16","cited_by_count":103,"area":"mllm"},{"id":"2302.08888","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","created":"2023-02-17","cited_by_count":86,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"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":"2309.02301","title":"CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning","created":"2023-09-05","cited_by_count":69,"area":"mllm"},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67,"area":"lr"},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51,"area":"mllm"},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"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":"2407.06438","title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","created":"2024-07-08","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":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2212.14454","title":"MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid","created":"2022-12-29","cited_by_count":30,"area":null},{"id":"2404.15272","title":"CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30,"area":"mllm"},{"id":"2308.07146","title":"CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation","created":"2023-08-14","cited_by_count":29,"area":"mllm"},{"id":"2502.07855","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","created":"2025-02-11","cited_by_count":29,"area":"mllm"},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2311.01487","title":"What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning","created":"2023-11-02","cited_by_count":28,"area":"lr"},{"id":"2411.18730","title":"Foundation Models in Radiology: What, How, When, Why and Why Not","created":"2024-11-27","cited_by_count":28,"area":null},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2303.12513","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","created":"2023-03-21","cited_by_count":20,"area":"lr"},{"id":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2410.22187","title":"Active Learning for Vision-Language Models","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2503.06973","title":"A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis","created":"2025-03-10","cited_by_count":15,"area":null},{"id":"2504.14280","title":"CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey","created":"2025-04-19","cited_by_count":15,"area":null},{"id":"2310.05861","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models","created":"2023-10-09","cited_by_count":14,"area":"lr"},{"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":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2504.04893","title":"SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models","created":"2025-04-07","cited_by_count":13,"area":"mllm"},{"id":"2407.19514","title":"Detached and Interactive Multimodal Learning","created":"2024-07-28","cited_by_count":11,"area":null},{"id":"2409.04758","title":"SGSeg: Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance","created":"2024-09-07","cited_by_count":11,"area":null},{"id":"2503.03987","title":"RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models","created":"2025-03-06","cited_by_count":10,"area":"mllm"},{"id":"2504.09480","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","created":"2025-04-13","cited_by_count":10,"area":"mllm"},{"id":"2303.15256","title":"Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need","created":"2023-03-27","cited_by_count":9,"area":null},{"id":"2311.15033","title":"Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones","created":"2023-11-25","cited_by_count":9,"area":null},{"id":"2506.00239","title":"SmellNet: A Large-scale Dataset for Real-world Smell Recognition","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2304.02853","title":"Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2306.09482","title":"Sample-Efficient Learning of Novel Visual Concepts","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2312.07255","title":"GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction","created":"2023-12-12","cited_by_count":8,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2403.08271","title":"Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification","created":"2024-03-13","cited_by_count":8,"area":"mllm"},{"id":"2306.07952","title":"MOFI: Learning Image Representations from Noisy Entity Annotated Images","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2412.12906","title":"CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2502.09906","title":"Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2306.09169","title":"Opportunities for Large Language Models and Discourse in Engineering Design","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2409.16145","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2411.18207","title":"From Open Vocabulary to Open World: Teaching Vision Language Models to Detect Novel Objects","created":"2024-11-27","cited_by_count":5,"area":"mllm"},{"id":"2507.05515","title":"LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2407.15316","title":"AI as a Tool for Fair Journalism: Case Studies from Malta","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2502.05568","title":"Large Multimodal Models for Low-Resource Languages: A Survey","created":"2025-02-08","cited_by_count":4,"area":"mllm"},{"id":"2403.06904","title":"Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2407.18715","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2504.13218","title":"Harmony: A Unified Framework for Modality Incremental Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2506.20494","title":"Multimodal Representation Learning and Fusion","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2604.10127","title":"VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2310.00783","title":"Propagating Semantic Labels in Video Data","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2405.17139","title":"Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2406.02780","title":"LADI v2: Multi-label Dataset and Classifiers for Low-Altitude Disaster Imagery","created":"2024-06-04","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":"2503.06626","title":"DiffCLIP: Differential Attention Meets CLIP","created":"2025-03-09","cited_by_count":2,"area":"mllm"},{"id":"2403.07888","title":"Cross-modality debiasing: using language to mitigate sub-population shifts in imaging","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2406.16093","title":"Towards Natural Language-Driven Assembly Using Foundation Models","created":"2024-06-23","cited_by_count":1,"area":"vla"},{"id":"2407.07771","title":"Multi-task Prompt Words Learning for Social Media Content Generation","created":"2024-07-10","cited_by_count":1,"area":null}],"next_cursor":"100"}