{"total":131,"rows":[{"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":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2602.06028","title":"Context Forcing: Consistent Autoregressive Video Generation with Long Context","created":"2026-02-05","cited_by_count":59,"area":null},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48,"area":null},{"id":"2510.05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","created":"2025-10-06","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":"2507.03905","title":"EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation","created":"2025-07-05","cited_by_count":29,"area":null},{"id":"2510.01784","title":"Pack and Force Your Memory: Long-form and Consistent Video Generation","created":"2025-10-02","cited_by_count":29,"area":null},{"id":"2510.13759","title":"Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2506.18899","title":"FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation","created":"2025-06-23","cited_by_count":28,"area":null},{"id":"2512.21094","title":"T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation","created":"2025-12-24","cited_by_count":24,"area":null},{"id":"2507.11245","title":"NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation","created":"2025-07-15","cited_by_count":22,"area":null},{"id":"2604.08540","title":"AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation","created":"2026-04-09","cited_by_count":21,"area":null},{"id":"2507.18107","title":"T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation","created":"2025-07-24","cited_by_count":19,"area":null},{"id":"2604.21915","title":"Vista4D: Video Reshooting with 4D Point Clouds","created":"2026-04-23","cited_by_count":18,"area":null},{"id":"2509.25182","title":"DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder","created":"2025-09-29","cited_by_count":16,"area":null},{"id":"2603.08703","title":"HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2604.08503","title":"Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics","created":"2026-04-09","cited_by_count":12,"area":null},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2505.21491","title":"Frame In-N-Out: Unbounded Controllable Image-to-Video Generation","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2512.12193","title":"SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation","created":"2025-12-13","cited_by_count":10,"area":null},{"id":"2601.14674","title":"LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models","created":"2026-01-21","cited_by_count":10,"area":null},{"id":"2602.05986","title":"RISE-Video: Can Video Generators Decode Implicit World Rules?","created":"2026-02-05","cited_by_count":10,"area":null},{"id":"2510.14847","title":"ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints","created":"2025-10-16","cited_by_count":9,"area":null},{"id":"2604.09415","title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","created":"2026-04-10","cited_by_count":9,"area":null},{"id":"2606.04527","title":"Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation","created":"2026-06-03","cited_by_count":9,"area":null},{"id":"2510.26412","title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2509.26555","title":"Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation","created":"2025-09-30","cited_by_count":6,"area":null},{"id":"2511.20635","title":"iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2512.21507","title":"SVBench: Evaluation of Video Generation Models on Social Reasoning","created":"2025-12-25","cited_by_count":6,"area":null},{"id":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2601.14161","title":"One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion","created":"2026-01-20","cited_by_count":6,"area":null},{"id":"2604.06939","title":"Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2605.15199","title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","created":"2026-05-14","cited_by_count":6,"area":null},{"id":"2605.26525","title":"ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2606.09639","title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","created":"2026-06-08","cited_by_count":6,"area":null},{"id":"2505.24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2512.01843","title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","created":"2025-12-01","cited_by_count":5,"area":null},{"id":"2601.00943","title":"PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education","created":"2026-01-02","cited_by_count":5,"area":null},{"id":"2605.23271","title":"EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation","created":"2026-05-22","cited_by_count":5,"area":null},{"id":"2507.04705","title":"Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2509.25187","title":"FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.07310","title":"MATRIX: Mask Track Alignment for Interaction-aware Video Generation","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2512.12430","title":"Endless World: Real-Time 3D-Aware Long Video Generation","created":"2025-12-13","cited_by_count":4,"area":null},{"id":"2512.22536","title":"CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation","created":"2025-12-27","cited_by_count":4,"area":null},{"id":"2601.04792","title":"PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference","created":"2026-01-08","cited_by_count":4,"area":null},{"id":"2603.00586","title":"WildActor: Unconstrained Identity-Preserving Video Generation","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2605.03475","title":"WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2507.22100","title":"Trade-offs in Image Generation: How Do Different Dimensions Interact?","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2512.03040","title":"Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2601.20504","title":"Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2603.02816","title":"BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2604.10127","title":"VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2605.14269","title":"PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2605.25659","title":"StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2607.18436","title":"Surprise Forcing: What to Remember, When to Skip in Long Video Generation","created":"2026-07-20","cited_by_count":3,"area":null},{"id":"2607.18924","title":"Learning Explicit Physical Parameter Control and Benchmarking for Video Generation","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2607.24241","title":"FilmBench: A Film-Grade Benchmark for Cinematic Video Generation","created":"2026-07-27","cited_by_count":3,"area":null},{"id":"2512.03918","title":"UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2603.29186","title":"SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2606.30557","title":"EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.15772","title":"SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation","created":"2026-07-17","cited_by_count":2,"area":null},{"id":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2608.09666","title":"Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2609.06207","title":"PhysWeep: Does a Video Generator Realize the Physics You Ask For?","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2505.20827","title":"Frame-Level Captions for Long Video Generation with Complex Multi Scenes","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2603.00173","title":"Summer-22B: A Systematic Approach to Dataset Engineering and Training at Scale for Video Foundation Model","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2604.15299","title":"AnimationBench: Are Video Models Good at Character-Centric Animation?","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.21931","title":"Seeing Fast and Slow: Learning the Flow of Time in Videos","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.14815","title":"Probing into Camera Control of Video Models","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.18591","title":"Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.24829","title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.25344","title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.01499","title":"Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.13527","title":"VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.14202","title":"KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.21848","title":"Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2607.24403","title":"GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.01942","title":"CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.13602","title":"Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.17426","title":"SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.20107","title":"BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2609.08275","title":"Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2610.01499","title":"VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2509.04450","title":"Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image -- Technical Preview","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.20182","title":"PEDRA: Evaluating the Realism of Pedestrian Dynamics in Video Generation","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.01803","title":"Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.18698","title":"Are Video Generation Models Geographically Fair? An Attraction-Centric Evaluation of Global Visual Knowledge","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.13669","title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.00585","title":"MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2604.07958","title":"ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.17428","title":"Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.25361","title":"HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.15116","title":"DriveCtrl: Conditioned Sim-to-Real Driving Video Generation","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15196","title":"RefDecoder: Enhancing Visual Generation with Conditional Video Decoding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.20731","title":"TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.26918","title":"Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.05665","title":"V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.14972","title":"ReGenHuman: Re-Generating Human Appearances for Realistic Full-Body Video Anonymization","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.26668","title":"Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":"100"}