{"total":62,"rows":[{"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":"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":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"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":"2410.05677","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","created":"2024-10-08","cited_by_count":54,"area":"diffusion"},{"id":"2412.04814","title":"LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment","created":"2024-12-06","cited_by_count":53,"area":"alignment"},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"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":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"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":"2507.00162","title":"FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion","created":"2025-06-30","cited_by_count":17,"area":null},{"id":"2502.01719","title":"MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation","created":"2025-02-03","cited_by_count":16,"area":"moe"},{"id":"2505.21653","title":"Think Before You Diffuse: Infusing Physical Rules into Video Diffusion","created":"2025-05-27","cited_by_count":16,"area":"lr"},{"id":"2508.09136","title":"Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices","created":"2025-08-12","cited_by_count":16,"area":null},{"id":"2501.07647","title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations","created":"2025-01-13","cited_by_count":15,"area":"diffusion"},{"id":"2502.04363","title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","created":"2025-02-05","cited_by_count":15,"area":"diffusion"},{"id":"2502.07590","title":"DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training","created":"2025-02-11","cited_by_count":15,"area":"diffusion"},{"id":"2502.02088","title":"Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation","created":"2025-02-04","cited_by_count":13,"area":"diffusion"},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"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":"2505.21491","title":"Frame In-N-Out: Unbounded Controllable Image-to-Video Generation","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9,"area":null},{"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":"2506.22434","title":"MiCo: Multi-image Contrast for Reinforcement Visual Reasoning","created":"2025-06-27","cited_by_count":9,"area":"lr"},{"id":"2606.16533","title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","created":"2026-06-15","cited_by_count":9,"area":"wm"},{"id":"2411.18375","title":"Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models","created":"2024-11-27","cited_by_count":8,"area":"diffusion"},{"id":"2602.09609","title":"Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing","created":"2026-02-10","cited_by_count":8,"area":"diffusion"},{"id":"2602.19161","title":"Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation","created":"2026-02-22","cited_by_count":7,"area":"diffusion"},{"id":"2605.25343","title":"Toward Native Multimodal Modeling: A Roadmap","created":"2026-05-25","cited_by_count":7,"area":"wm"},{"id":"2510.02571","title":"How Confident are Video Models? Empowering Video Models to Express their Uncertainty","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2511.18382","title":"ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access","created":"2025-11-23","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":"2504.09789","title":"On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise","created":"2025-04-14","cited_by_count":5,"area":"diffusion"},{"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":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2602.06130","title":"Self-Improving World Modelling with Latent Actions","created":"2026-02-05","cited_by_count":5,"area":"wm"},{"id":"2604.24762","title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2507.01938","title":"CI-VID: A Coherent Interleaved Text-Video Dataset","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2601.04068","title":"Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models","created":"2026-01-07","cited_by_count":4,"area":"diffusion"},{"id":"2608.09449","title":"Sekai2: From World Exploration to Interactive World Modeling","created":"2026-08-10","cited_by_count":3,"area":"wm"},{"id":"2508.04228","title":"LayerT2V: A Unified Multi-Layer Video Generation Framework","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2512.13015","title":"What Happens Next? Next Scene Prediction with a Unified Video Model","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2601.06309","title":"VideoWeave: A Data-Centric Approach for Efficient Video Understanding","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.01624","title":"PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2603.10685","title":"A$^2$-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.21489","title":"Variance Reduction for Expectations with Diffusion Teachers","created":"2026-05-20","cited_by_count":2,"area":"diffusion"},{"id":"2606.03168","title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2503.14002","title":"MeshFleet: Filtered and Annotated 3D Vehicle Dataset for Domain Specific Generative Modeling","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2503.17539","title":"Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks","created":"2025-03-21","cited_by_count":1,"area":"diffusion"},{"id":"2511.14229","title":"EBind: a practical approach to space binding","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2603.14073","title":"MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2604.01700","title":"Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation","created":"2026-04-02","cited_by_count":1,"area":"diffusion"},{"id":"2604.07230","title":"PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing","created":"2026-04-08","cited_by_count":1,"area":"wm"},{"id":"2606.04737","title":"Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment","created":"2026-06-03","cited_by_count":1,"area":"diffusion"},{"id":"2606.19408","title":"FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2503.23796","title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","created":"2025-03-31","cited_by_count":0,"area":"diffusion"},{"id":"2510.17519","title":"MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2602.17260","title":"EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.05539","title":"VDCook:DIY video data cook your MLLMs","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2607.19437","title":"Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.24845","title":"LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}