{"list":"other","total":67,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2501.18362","title":"MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding","created":"2025-01-30","cited_by_count":224},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2505.17685","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","created":"2025-05-23","cited_by_count":166},{"id":"2406.07394","title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","created":"2024-06-11","cited_by_count":158},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115},{"id":"2406.14228","title":"EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms","created":"2024-06-20","cited_by_count":113},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74},{"id":"2501.12368","title":"InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model","created":"2025-01-21","cited_by_count":74},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73},{"id":"2501.13468","title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","created":"2025-01-23","cited_by_count":73},{"id":"1707.03067","title":"Automatic Understanding of Image and Video Advertisements","created":"2017-07-10","cited_by_count":68},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2312.02439","title":"Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation","created":"2023-12-05","cited_by_count":56},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55},{"id":"2012.05710","title":"Look Before you Speak: Visually Contextualized Utterances","created":"2020-12-10","cited_by_count":53},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45},{"id":"2311.14906","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","created":"2023-11-25","cited_by_count":40},{"id":"2411.16345","title":"Preference Optimization for Reasoning with Pseudo Feedback","created":"2024-11-25","cited_by_count":39},{"id":"2504.13092","title":"EventVAD: Training-Free Event-Aware Video Anomaly Detection","created":"2025-04-17","cited_by_count":36},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35},{"id":"2407.05355","title":"VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool","created":"2024-07-07","cited_by_count":35},{"id":"2407.08940","title":"Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation","created":"2024-07-12","cited_by_count":34},{"id":"2501.10332","title":"Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems","created":"2025-01-17","cited_by_count":32},{"id":"2212.09898","title":"MetaCLUE: Towards Comprehensive Visual Metaphors Research","created":"2022-12-19","cited_by_count":28},{"id":"2502.06428","title":"CoS: Chain-of-Shot Prompting for Long Video Understanding","created":"2025-02-10","cited_by_count":27},{"id":"2011.05558","title":"Intentonomy: a Dataset and Study towards Human Intent Understanding","created":"2020-11-11","cited_by_count":22},{"id":"2405.14040","title":"Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline","created":"2024-05-22","cited_by_count":19},{"id":"2502.16641","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","created":"2025-02-23","cited_by_count":13},{"id":"2312.14055","title":"Multi-Sentence Grounding for Long-term Instructional Video","created":"2023-12-21","cited_by_count":10},{"id":"2505.15616","title":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models","created":"2025-05-21","cited_by_count":9},{"id":"2305.18373","title":"KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models","created":"2023-05-28","cited_by_count":7}],"next_cursor":null}