{"total":253,"rows":[{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080,"area":null},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233,"area":null},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201,"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":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148,"area":null},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138,"area":null},{"id":"2403.03174","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","created":"2024-03-05","cited_by_count":129,"area":null},{"id":"2311.01361","title":"GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks","created":"2023-11-02","cited_by_count":119,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96,"area":null},{"id":"2402.18659","title":"Large Language Models and Games: A Survey and Roadmap","created":"2024-02-28","cited_by_count":93,"area":null},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"area":null},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2401.07314","title":"MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation","created":"2024-01-14","cited_by_count":86,"area":null},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2312.06281","title":"EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models","created":"2023-12-11","cited_by_count":80,"area":null},{"id":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79,"area":null},{"id":"2310.09909","title":"Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis","created":"2023-10-15","cited_by_count":77,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2401.16402","title":"A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect","created":"2024-01-29","cited_by_count":69,"area":null},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66,"area":null},{"id":"2310.03602","title":"Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints","created":"2023-10-05","cited_by_count":60,"area":null},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2407.04689","title":"RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation","created":"2024-07-05","cited_by_count":58,"area":null},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57,"area":null},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52,"area":null},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51,"area":null},{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51,"area":null},{"id":"2412.10137","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","created":"2024-12-13","cited_by_count":50,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"area":null},{"id":"2404.04242","title":"Physical Property Understanding from Language-Embedded Feature Fields","created":"2024-04-05","cited_by_count":48,"area":null},{"id":"2311.00571","title":"LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing","created":"2023-11-01","cited_by_count":47,"area":null},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2412.09604","title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding","created":"2024-12-12","cited_by_count":42,"area":null},{"id":"2504.14603","title":"UFO2: The Desktop AgentOS","created":"2025-04-20","cited_by_count":41,"area":null},{"id":"2311.02782","title":"Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead","created":"2023-11-05","cited_by_count":40,"area":null},{"id":"2310.08541","title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2404.09349","title":"Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies","created":"2024-04-14","cited_by_count":38,"area":null},{"id":"2310.20381","title":"A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis","created":"2023-10-31","cited_by_count":37,"area":null},{"id":"2311.15732","title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","created":"2023-11-27","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2407.05603","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","created":"2024-07-08","cited_by_count":34,"area":null},{"id":"2403.05854","title":"LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content","created":"2024-03-09","cited_by_count":33,"area":null},{"id":"2312.05735","title":"A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learning","created":"2023-12-10","cited_by_count":32,"area":null},{"id":"2403.19584","title":"Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation","created":"2024-03-28","cited_by_count":32,"area":null},{"id":"2411.12789","title":"Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting","created":"2024-11-19","cited_by_count":32,"area":null},{"id":"2310.16534","title":"An Early Evaluation of GPT-4V(ision)","created":"2023-10-25","cited_by_count":31,"area":null},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31,"area":null},{"id":"2411.17673","title":"SketchAgent: Language-Driven Sequential Sketch Generation","created":"2024-11-26","cited_by_count":31,"area":null},{"id":"2505.02388","title":"MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans","created":"2025-05-05","cited_by_count":31,"area":null},{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"area":null},{"id":"2406.04983","title":"CityCraft: A Real Crafter for 3D City Generation","created":"2024-06-07","cited_by_count":26,"area":null},{"id":"2511.19046","title":"MedSAM3: Delving into Segment Anything with Medical Concepts","created":"2025-11-24","cited_by_count":26,"area":null},{"id":"2407.16670","title":"FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process","created":"2024-07-23","cited_by_count":25,"area":null},{"id":"2411.15122","title":"ReXrank: A Public Leaderboard for AI-Powered Radiology Report Generation","created":"2024-11-22","cited_by_count":25,"area":null},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25,"area":null},{"id":"2406.16386","title":"Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach","created":"2024-06-24","cited_by_count":24,"area":null},{"id":"2411.05383","title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","created":"2024-11-08","cited_by_count":24,"area":null},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23,"area":null},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"area":null},{"id":"2505.00693","title":"Robotic Visual Instruction","created":"2025-05-01","cited_by_count":22,"area":null},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2311.13596","title":"T-Rex: Counting by Visual Prompting","created":"2023-11-22","cited_by_count":20,"area":null},{"id":"2403.11083","title":"Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning","created":"2024-03-17","cited_by_count":20,"area":null},{"id":"2403.14487","title":"DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing","created":"2024-03-21","cited_by_count":20,"area":null},{"id":"2312.05256","title":"Holistic Evaluation of GPT-4V for Biomedical Imaging","created":"2023-11-10","cited_by_count":19,"area":null},{"id":"2403.16831","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2410.00467","title":"Dynamic Planning for LLM-based Graphical User Interface Automation","created":"2024-10-01","cited_by_count":19,"area":null},{"id":"2312.07044","title":"Large Foundation Models for Power Systems","created":"2023-12-12","cited_by_count":18,"area":null},{"id":"2401.04124","title":"MobileAgent: enhancing mobile control via human-machine interaction and SOP integration","created":"2024-01-04","cited_by_count":18,"area":null},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2412.02621","title":"Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions","created":"2024-12-03","cited_by_count":18,"area":null},{"id":"2412.10047","title":"Large Action Models: From Inception to Implementation","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2310.15144","title":"DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2403.17368","title":"ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2310.07749","title":"OpenLEAF: Open-Domain Interleaved Image-Text Generation and Evaluation","created":"2023-10-11","cited_by_count":16,"area":null},{"id":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","cited_by_count":16,"area":null},{"id":"2312.17016","title":"On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications","created":"2023-12-23","cited_by_count":15,"area":null},{"id":"2402.01662","title":"Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives","created":"2024-01-14","cited_by_count":15,"area":null},{"id":"2412.04237","title":"VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction","created":"2024-12-05","cited_by_count":15,"area":null},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2507.01955","title":"How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks","created":"2025-07-02","cited_by_count":14,"area":null},{"id":"2311.12990","title":"NERIF: GPT-4V for Automatic Scoring of Drawn Models","created":"2023-11-21","cited_by_count":13,"area":null},{"id":"2311.13018","title":"GeoLocator: a location-integrated large multimodal model for inferring geo-privacy","created":"2023-11-21","cited_by_count":13,"area":null},{"id":"2402.12525","title":"LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2403.00209","title":"ChartReformer: Natural Language-Driven Chart Image Editing","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2403.04822","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","created":"2024-03-07","cited_by_count":13,"area":null},{"id":"2407.10947","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","created":"2024-07-15","cited_by_count":13,"area":null},{"id":"2401.08660","title":"Gemini Pro Defeated by GPT-4V: Evidence from Education","created":"2023-12-27","cited_by_count":12,"area":null},{"id":"2403.06420","title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2404.03429","title":"Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2405.13049","title":"SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations","created":"2024-05-19","cited_by_count":12,"area":null}],"next_cursor":"100"}