{"total":185,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347,"area":null},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123,"area":null},{"id":"2303.08559","title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","created":"2023-03-15","cited_by_count":119,"area":null},{"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":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2305.15023","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":101,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83,"area":null},{"id":"2310.09881","title":"In-Context Learning with Iterative Demonstration Selection","created":"2023-10-15","cited_by_count":74,"area":null},{"id":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68,"area":null},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2402.03182","title":"Empowering Time Series Analysis with Large Language Models: A Survey","created":"2024-02-05","cited_by_count":60,"area":null},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56,"area":null},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51,"area":null},{"id":"2311.06495","title":"LayoutPrompter: Awaken the Design Ability of Large Language Models","created":"2023-11-11","cited_by_count":48,"area":null},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44,"area":null},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43,"area":null},{"id":"2312.05038","title":"Prompt-In-Prompt Learning for Universal Image Restoration","created":"2023-12-08","cited_by_count":43,"area":null},{"id":"2310.17110","title":"LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?","created":"2023-10-26","cited_by_count":40,"area":null},{"id":"2305.04757","title":"Augmented Large Language Models with Parametric Knowledge Guiding","created":"2023-05-08","cited_by_count":37,"area":null},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36,"area":null},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2411.17673","title":"SketchAgent: Language-Driven Sequential Sketch Generation","created":"2024-11-26","cited_by_count":31,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2308.14316","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","created":"2023-08-28","cited_by_count":26,"area":null},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26,"area":null},{"id":"2308.01285","title":"Flows: Building Blocks of Reasoning and Collaborating AI","created":"2023-08-02","cited_by_count":25,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2405.05615","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","created":"2024-05-09","cited_by_count":20,"area":null},{"id":"2408.12880","title":"Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey","created":"2024-08-23","cited_by_count":20,"area":null},{"id":"2401.08694","title":"Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation","created":"2024-01-13","cited_by_count":19,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2512.10941","title":"Mull-Tokens: Modality-Agnostic Latent Thinking","created":"2025-12-11","cited_by_count":19,"area":null},{"id":"2309.04790","title":"MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images","created":"2023-09-09","cited_by_count":18,"area":null},{"id":"2401.13298","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2310.07328","title":"An Empirical Study of Instruction-tuning Large Language Models in Chinese","created":"2023-10-11","cited_by_count":17,"area":null},{"id":"2310.12020","title":"LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation","created":"2023-10-18","cited_by_count":17,"area":null},{"id":"2404.08704","title":"MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting","created":"2024-04-11","cited_by_count":15,"area":null},{"id":"2308.13785","title":"ORES: Open-vocabulary Responsible Visual Synthesis","created":"2023-08-26","cited_by_count":14,"area":null},{"id":"2311.03754","title":"Which is better? Exploring Prompting Strategy For LLM-based Metrics","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2503.19611","title":"Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation","created":"2025-03-25","cited_by_count":14,"area":null},{"id":"2505.16836","title":"Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning","created":"2025-05-22","cited_by_count":14,"area":null},{"id":"2412.12107","title":"Generative AI Literacy: Twelve Defining Competencies","created":"2024-11-29","cited_by_count":13,"area":null},{"id":"2412.19712","title":"From Elements to Design: A Layered Approach for Automatic Graphic Design Composition","created":"2024-12-27","cited_by_count":13,"area":null},{"id":"2306.10765","title":"Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost","created":"2023-06-19","cited_by_count":12,"area":null},{"id":"2308.09033","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2405.11215","title":"MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing","created":"2024-05-18","cited_by_count":12,"area":null},{"id":"2406.05806","title":"Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper","created":"2024-06-09","cited_by_count":12,"area":null},{"id":"2501.01243","title":"Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2506.13045","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2404.15790","title":"Leveraging Large Language Models for Multimodal Search","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2407.07523","title":"SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning","created":"2024-07-10","cited_by_count":11,"area":null},{"id":"2407.19196","title":"Why Misinformation is Created? Detecting them by Integrating Intent Features","created":"2024-07-27","cited_by_count":11,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2412.16936","title":"Rationale-guided Prompting for Knowledge-based Visual Question Answering","created":"2024-12-22","cited_by_count":9,"area":null},{"id":"2309.15630","title":"NLPBench: Evaluating Large Language Models on Solving NLP Problems","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2312.14206","title":"LLM4VG: Large Language Models Evaluation for Video Grounding","created":"2023-12-21","cited_by_count":8,"area":null},{"id":"2406.10228","title":"VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2407.03967","title":"Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2305.12943","title":"Album Storytelling with Iterative Story-aware Captioning and Large Language Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2308.09970","title":"Tackling Vision Language Tasks Through Learning Inner Monologues","created":"2023-08-19","cited_by_count":7,"area":null},{"id":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2503.02341","title":"GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2508.09560","title":"WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2508.09566","title":"A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2510.09201","title":"Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs","created":"2025-10-10","cited_by_count":7,"area":null},{"id":"2603.12829","title":"coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation","created":"2026-03-13","cited_by_count":7,"area":null},{"id":"2402.10534","title":"Using Left and Right Brains Together: Towards Vision and Language Planning","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2405.18004","title":"SkinCaRe: A Multimodal Dermatology Dataset Annotated with Medical Caption and Chain-of-Thought Reasoning","created":"2024-05-28","cited_by_count":6,"area":null},{"id":"2407.15842","title":"DiffArtist: Towards Structure and Appearance Controllable Image Stylization","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2501.06386","title":"Using Pre-trained LLMs for Multivariate Time Series Forecasting","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2503.04506","title":"Multi-modal Summarization in Model-Based Engineering: Automotive Software Development Case Study","created":"2025-03-06","cited_by_count":6,"area":null},{"id":"2510.27195","title":"Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions","created":"2025-10-31","cited_by_count":6,"area":null},{"id":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2311.09612","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2311.11695","title":"Clarity ChatGPT: An Interactive and Adaptive Processing System for Image Restoration and Enhancement","created":"2023-11-20","cited_by_count":5,"area":null},{"id":"2410.12284","title":"Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2507.15025","title":"Survey of GenAI for Automotive Software Development: From Requirements to Executable Code","created":"2025-07-20","cited_by_count":5,"area":null}],"next_cursor":"100"}