{"total":116,"rows":[{"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":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2406.15252","title":"VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation","created":"2024-06-21","cited_by_count":197,"area":null},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174,"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":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129,"area":null},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93,"area":null},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71,"area":null},{"id":"2411.05003","title":"ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning","created":"2024-11-07","cited_by_count":70,"area":null},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69,"area":null},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68,"area":null},{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67,"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":"2408.02629","title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","created":"2024-08-05","cited_by_count":62,"area":null},{"id":"2402.04290","title":"CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling","created":"2024-02-06","cited_by_count":56,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2503.19907","title":"FullDiT: Multi-Task Video Generative Foundation Model with Full Attention","created":"2025-03-25","cited_by_count":47,"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":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43,"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":"2411.06525","title":"I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength","created":"2024-11-10","cited_by_count":39,"area":null},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36,"area":null},{"id":"2404.06637","title":"GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis","created":"2024-04-09","cited_by_count":32,"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":"2505.20287","title":"MotionPro: A Precise Motion Controller for Image-to-Video Generation","created":"2025-05-26","cited_by_count":30,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","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":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2503.17934","title":"TransAnimate: Taming Layer Diffusion to Generate RGBA Video","created":"2025-03-23","cited_by_count":24,"area":null},{"id":"2503.20172","title":"Guiding Human-Object Interactions with Rich Geometry and Relations","created":"2025-03-26","cited_by_count":24,"area":null},{"id":"2503.01103","title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23,"area":null},{"id":"2501.06006","title":"CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control","created":"2025-01-10","cited_by_count":21,"area":null},{"id":"2407.00367","title":"SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix","created":"2024-06-29","cited_by_count":20,"area":null},{"id":"2411.17765","title":"I2VControl: Disentangled and Unified Video Motion Synthesis Control","created":"2024-11-26","cited_by_count":20,"area":null},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2404.12347","title":"AniClipart: Clipart Animation with Text-to-Video Priors","created":"2024-04-18","cited_by_count":17,"area":null},{"id":"2506.23361","title":"OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions","created":"2025-06-29","cited_by_count":17,"area":null},{"id":"2410.04081","title":"Epsilon-VAE: Denoising as Visual Decoding","created":"2024-10-05","cited_by_count":16,"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":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2510.20888","title":"Video-As-Prompt: Unified Semantic Control for Video Generation","created":"2025-10-23","cited_by_count":14,"area":null},{"id":"2504.11389","title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2411.11934","title":"SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2504.02451","title":"ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2505.00209","title":"Direct Motion Models for Assessing Generated Videos","created":"2025-04-30","cited_by_count":10,"area":null},{"id":"2505.13437","title":"FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2506.19488","title":"SceneCrafter: Controllable Multi-View Driving Scene Editing","created":"2025-06-24","cited_by_count":9,"area":null},{"id":"2412.00730","title":"SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2412.01987","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2412.10255","title":"AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era","created":"2024-12-13","cited_by_count":8,"area":null},{"id":"2501.08303","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2512.12196","title":"AutoMV: An Automatic Multi-Agent System for Music Video Generation","created":"2025-12-13","cited_by_count":8,"area":null},{"id":"2409.19862","title":"Learning Multimodal Latent Generative Models with Energy-Based Prior","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2412.16155","title":"Can Generative Video Models Help Pose Estimation?","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2603.12267","title":"EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2407.20592","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos","created":"2024-07-30","cited_by_count":6,"area":null},{"id":"2411.14762","title":"Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction","created":"2024-11-22","cited_by_count":6,"area":null},{"id":"2503.06053","title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2503.09949","title":"UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2505.00135","title":"Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis","created":"2025-04-30","cited_by_count":6,"area":null},{"id":"2506.08456","title":"Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2606.30599","title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2409.02529","title":"Sample what you cant compress","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2411.04967","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2504.19834","title":"AnimateAnywhere: Rouse the Background in Human Image Animation","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2506.05343","title":"ContentV: Efficient Training of Video Generation Models with Limited Compute","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2510.02226","title":"TempoControl: Temporal Attention Guidance for Text-to-Video Models","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2604.01015","title":"Forecasting Motion in the Wild","created":"2026-04-01","cited_by_count":5,"area":null},{"id":"2507.13942","title":"Frozen Forecasting: A Unified Evaluation","created":"2025-07-18","cited_by_count":4,"area":null},{"id":"2510.08458","title":"SummDiff: Generative Modeling of Video Summarization with Diffusion","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.02107","title":"MagicFight: Personalized Martial Arts Combat Video Generation","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2602.10095","title":"Causality in Video Diffusers is Separable from Denoising","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2406.17809","title":"Towards a Science Exocortex","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2412.18966","title":"ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2512.14938","title":"TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2407.15153","title":"Anchored Diffusion for Video Face Reenactment","created":"2024-07-21","cited_by_count":2,"area":null},{"id":"2411.10503","title":"Everything is a Video: Unifying Modalities through Next-Frame Prediction","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2503.09279","title":"Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2507.04559","title":"MambaVideo for Discrete Video Tokenization with Channel-Split Quantization","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2507.13224","title":"Leveraging Pre-Trained Visual Models for AI-Generated Video Detection","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2510.07441","title":"DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2510.16791","title":"Personalized Image Filter: Mastering Your Photographic Style","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2409.01502","title":"AMG: Avatar Motion Guided Video Generation","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2505.22046","title":"LatentMove: Towards Complex Human Movement Video Generation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.00334","title":"Populate-A-Scene: Affordance-Aware Human Video Generation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2603.06289","title":"FlowMotion: Training-Free Flow Guidance for Video Motion Transfer","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.18331","title":"Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equations","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.28491","title":"DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.07508","title":"Streaming Video Generation with Streaming Force Control","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null}],"next_cursor":"100"}