{"total":117,"rows":[{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517,"area":"lr"},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196,"area":"lr"},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175,"area":null},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153,"area":"alignment"},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"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":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87,"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":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"id":"2305.02317","title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","created":"2023-05-03","cited_by_count":69,"area":"lr"},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53,"area":"mllm"},{"id":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51,"area":"lr"},{"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":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50,"area":null},{"id":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50,"area":"mllm"},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"id":"2312.10160","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","created":"2023-12-15","cited_by_count":49,"area":"mllm"},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2302.04449","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","created":"2023-02-09","cited_by_count":45,"area":null},{"id":"2311.10678","title":"Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections","created":"2023-11-17","cited_by_count":45,"area":null},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45,"area":null},{"id":"2305.12328","title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","created":"2023-05-21","cited_by_count":44,"area":null},{"id":"2412.04447","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","created":"2024-12-05","cited_by_count":41,"area":"lr"},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2404.09797","title":"TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding","created":"2024-04-15","cited_by_count":38,"area":"lr"},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2403.04306","title":"Effectiveness Assessment of Recent Large Vision-Language Models","created":"2024-03-07","cited_by_count":29,"area":"mllm"},{"id":"2210.04287","title":"Learning to Decompose Visual Features with Latent Textual Prompts","created":"2022-10-09","cited_by_count":28,"area":"mllm"},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2211.08473","title":"On the Compositional Generalization Gap of In-Context Learning","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2407.06842","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","created":"2024-07-09","cited_by_count":19,"area":"mllm"},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2507.00950","title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","created":"2025-07-01","cited_by_count":14,"area":null},{"id":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13,"area":"mllm"},{"id":"2310.05872","title":"ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models","created":"2023-10-09","cited_by_count":12,"area":"lr"},{"id":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2402.10698","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","created":"2024-02-16","cited_by_count":9,"area":"mllm"},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2504.07454","title":"How Can Objects Help Video-Language Understanding?","created":"2025-04-10","cited_by_count":8,"area":"mllm"},{"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":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2304.03754","title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","created":"2023-04-07","cited_by_count":6,"area":null},{"id":"2307.04643","title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2312.02249","title":"Recursive Visual Programming","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2510.07915","title":"MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding","created":"2025-10-09","cited_by_count":6,"area":"inference"},{"id":"2305.13782","title":"Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2312.13503","title":"InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2403.01777","title":"NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision","created":"2024-03-04","cited_by_count":5,"area":"lr"},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2409.19508","title":"Transforming Scholarly Landscapes: Influence of Large Language Models on Academic Fields beyond Computer Science","created":"2024-09-29","cited_by_count":4,"area":null},{"id":"2502.15009","title":"Contextualizing Search Queries In-Context Learning for Conversational Rewriting with LLMs","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2410.11702","title":"It's Just Another Day: Unique Video Captioning by Discriminative Prompting","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2502.17589","title":"End-to-End Chart Summarization via Visual Chain-of-Thought in Vision-Language Models","created":"2025-02-24","cited_by_count":3,"area":"lr"},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2507.16951","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"id":"2404.04763","title":"GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2406.11190","title":"Aligning Large Language Models from Self-Reference AI Feedback with one General Principle","created":"2024-06-17","cited_by_count":2,"area":"alignment"},{"id":"2411.04059","title":"Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2501.18269","title":"MAMS: Model-Agnostic Module Selection Framework for Video Captioning","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2503.08842","title":"Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.18407","title":"VTD-CLIP: Video-to-Text Discretization via Prompting CLIP","created":"2025-03-24","cited_by_count":2,"area":"mllm"},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2508.14395","title":"NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2207.01823","title":"Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2403.13666","title":"Grounding Spatial Relations in Text-Only Language Models","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2406.03843","title":"POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models","created":"2024-06-06","cited_by_count":1,"area":"lr"},{"id":"2406.10923","title":"Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies","created":"2024-06-16","cited_by_count":1,"area":"lr"},{"id":"2408.06874","title":"Leveraging Language Models for Emotion and Behavior Analysis in Education","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2410.02959","title":"Coal Mining Question Answering with LLMs","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2412.01115","title":"DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding","created":"2024-12-02","cited_by_count":1,"area":"rag"}],"next_cursor":"100"}