{"total":263,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255,"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":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"area":null},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"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":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86,"area":null},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","cited_by_count":86,"area":null},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77,"area":null},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73,"area":null},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70,"area":null},{"id":"2407.01094","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","created":"2024-07-01","cited_by_count":67,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2506.13691","title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","created":"2025-06-16","cited_by_count":57,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2509.20360","title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","created":"2025-09-24","cited_by_count":54,"area":null},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54,"area":null},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45,"area":null},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44,"area":null},{"id":"2406.08656","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","created":"2024-06-12","cited_by_count":43,"area":null},{"id":"2410.00741","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","created":"2024-10-01","cited_by_count":41,"area":null},{"id":"2411.08380","title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","created":"2024-11-13","cited_by_count":41,"area":null},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40,"area":null},{"id":"2403.11956","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","created":"2024-03-18","cited_by_count":39,"area":null},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35,"area":null},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2506.15691","title":"What Do Latent Action Models Actually Learn?","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2512.09299","title":"VABench: A Comprehensive Benchmark for Audio-Video Generation","created":"2025-12-10","cited_by_count":30,"area":null},{"id":"2407.13773","title":"OpenDataLab: Empowering General Artificial Intelligence with Open Datasets","created":"2024-06-04","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2408.16219","title":"Training-free Video Temporal Grounding using Large-scale Pre-trained Models","created":"2024-08-29","cited_by_count":28,"area":null},{"id":"2503.14151","title":"Concat-ID: Towards Universal Identity-Preserving Video Synthesis","created":"2025-03-18","cited_by_count":28,"area":null},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"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":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2410.10816","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2405.15343","title":"Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Features","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2503.01739","title":"VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2503.19009","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","created":"2025-03-24","cited_by_count":20,"area":null},{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2405.07425","title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","created":"2024-05-13","cited_by_count":17,"area":null},{"id":"2412.09283","title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption","created":"2024-12-12","cited_by_count":17,"area":null},{"id":"2507.00162","title":"FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion","created":"2025-06-30","cited_by_count":17,"area":null},{"id":"2404.04933","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2510.18573","title":"Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model","created":"2025-10-21","cited_by_count":16,"area":null},{"id":"2512.16906","title":"VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization","created":"2025-12-18","cited_by_count":16,"area":null},{"id":"2405.19818","title":"WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark","created":"2024-05-30","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15,"area":null},{"id":"2508.08601","title":"Yan: Foundational Interactive Video Generation","created":"2025-08-12","cited_by_count":15,"area":null},{"id":"2310.01324","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","created":"2023-10-02","cited_by_count":14,"area":null},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13,"area":null},{"id":"2512.16920","title":"EasyV2V: A High-quality Instruction-based Video Editing Framework","created":"2025-12-18","cited_by_count":13,"area":null},{"id":"2405.13824","title":"GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2407.06491","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2409.04732","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","created":"2024-09-07","cited_by_count":12,"area":null},{"id":"2410.10719","title":"4-LEGS: 4D Language Embedded Gaussian Splatting","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2411.16156","title":"VideoOrion: Tokenizing Object Dynamics in Videos","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2501.14755","title":"Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2402.07127","title":"Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation","created":"2024-02-11","cited_by_count":11,"area":null},{"id":"2411.18983","title":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing","created":"2024-11-28","cited_by_count":11,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2602.03589","title":"SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM","created":"2026-02-03","cited_by_count":11,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2403.03194","title":"MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2406.11253","title":"Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null}],"next_cursor":"100"}