{"total":75,"rows":[{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261,"area":"wm"},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"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":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174,"area":null},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158,"area":null},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156,"area":null},{"id":"2412.14167","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation","created":"2024-12-18","cited_by_count":108,"area":"diffusion"},{"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":"2408.17065","title":"Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning","created":"2024-08-30","cited_by_count":59,"area":null},{"id":"2411.17459","title":"WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model","created":"2024-11-26","cited_by_count":57,"area":"diffusion"},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2410.20502","title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation","created":"2024-10-27","cited_by_count":41,"area":"diffusion"},{"id":"2412.10891","title":"Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection","created":"2024-12-14","cited_by_count":41,"area":"diffusion"},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"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":"2409.01199","title":"OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model","created":"2024-09-02","cited_by_count":30,"area":"diffusion"},{"id":"2412.16211","title":"Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation","created":"2024-12-17","cited_by_count":30,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2503.23452","title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","created":"2025-03-30","cited_by_count":23,"area":"agents"},{"id":"2505.15145","title":"CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation","created":"2025-05-21","cited_by_count":23,"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":"2503.10391","title":"CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance","created":"2025-03-13","cited_by_count":19,"area":"diffusion"},{"id":"2503.13319","title":"MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis","created":"2025-03-17","cited_by_count":19,"area":"diffusion"},{"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":"2606.00793","title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","created":"2026-05-30","cited_by_count":18,"area":"wm"},{"id":"2606.20545","title":"Current World Models Lack a Persistent State Core","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2606.27537","title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","created":"2026-06-25","cited_by_count":12,"area":"wm"},{"id":"2410.04171","title":"IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis","created":"2024-10-05","cited_by_count":10,"area":"diffusion"},{"id":"2504.04051","title":"Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models","created":"2025-04-05","cited_by_count":10,"area":"diffusion"},{"id":"2504.21650","title":"HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation","created":"2025-04-30","cited_by_count":10,"area":"diffusion"},{"id":"2602.05986","title":"RISE-Video: Can Video Generators Decode Implicit World Rules?","created":"2026-02-05","cited_by_count":10,"area":null},{"id":"2410.05255","title":"Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization","created":"2024-10-07","cited_by_count":9,"area":"diffusion"},{"id":"2503.16867","title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering","created":"2025-03-21","cited_by_count":9,"area":"alignment"},{"id":"2505.23484","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","created":"2025-05-29","cited_by_count":9,"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":"2602.10113","title":"ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2605.27589","title":"What-If World: A Causal Benchmark for General World Models in Embodied Scenarios","created":"2026-05-26","cited_by_count":8,"area":"wm"},{"id":"2503.14941","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","created":"2025-03-19","cited_by_count":7,"area":"mllm"},{"id":"2510.06231","title":"CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2604.06339","title":"Evolution of Video Generative Foundations","created":"2026-04-07","cited_by_count":7,"area":"wm"},{"id":"2606.11670","title":"ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation","created":"2026-06-10","cited_by_count":7,"area":null},{"id":"2506.14404","title":"Causally Steered Diffusion for Automated Video Counterfactual Generation","created":"2025-06-17","cited_by_count":6,"area":"diffusion"},{"id":"2506.23729","title":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization","created":"2025-06-30","cited_by_count":6,"area":null},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"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":"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":"2510.03886","title":"Rare Text Semantics Were Always There in Your Diffusion Transformer","created":"2025-10-04","cited_by_count":4,"area":"diffusion"},{"id":"2512.05969","title":"Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices","created":"2025-11-02","cited_by_count":4,"area":null},{"id":"2604.26503","title":"Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models","created":"2026-04-29","cited_by_count":4,"area":"diffusion"},{"id":"2502.17863","title":"A Survey: Spatiotemporal Consistency in Video Generation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2506.16119","title":"FastInit: Fast Noise Initialization for Temporally Consistent Video Generation","created":"2025-06-19","cited_by_count":3,"area":"diffusion"},{"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":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2506.04715","title":"Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2509.17808","title":"Remote Sensing-Oriented World Model","created":"2025-09-22","cited_by_count":2,"area":"wm"},{"id":"2409.17093","title":"BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2604.07990","title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.23536","title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","created":"2026-04-26","cited_by_count":1,"area":"diffusion"},{"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":"2410.05804","title":"CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection","created":"2024-10-08","cited_by_count":0,"area":"mllm"},{"id":"2503.09154","title":"SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2503.14428","title":"Comp-Attn: Present-and-Align Attention for Compositional Video Generation","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2503.18583","title":"Adapting Video Diffusion Models for Time-Lapse Microscopy","created":"2025-03-24","cited_by_count":0,"area":"diffusion"},{"id":"2601.19236","title":"VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.01340","title":"MTC-VAE: Multi-Level Temporal Compression with Content Awareness","created":"2026-02-01","cited_by_count":0,"area":"diffusion"},{"id":"2603.06165","title":"Reflective Flow Sampling Enhancement","created":"2026-03-06","cited_by_count":0,"area":"diffusion"},{"id":"2604.16405","title":"ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models","created":"2026-03-31","cited_by_count":0,"area":"wm"},{"id":"2608.00617","title":"Diagnosing Under-Development of Irreversible Processes in Video Generation","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.16513","title":"MLLM-Guided Semantic Correction for Text-to-Video Generation","created":"2026-08-17","cited_by_count":0,"area":"diffusion"},{"id":"2608.25452","title":"VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.33723","title":"GeoShrink: Accelerating Diffusion Transformers with Two Lines of Code","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2610.19823","title":"PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}