{"total":57,"rows":[{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229,"area":"mllm"},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168,"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":"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":"2505.23742","title":"MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement","created":"2025-05-29","cited_by_count":23,"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":"2503.14325","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","created":"2025-03-18","cited_by_count":17,"area":"diffusion"},{"id":"2412.17726","title":"VidTwin: Video VAE with Decoupled Structure and Dynamics","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2504.10567","title":"H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models","created":"2025-04-14","cited_by_count":13,"area":"diffusion"},{"id":"2504.06982","title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","created":"2025-04-09","cited_by_count":12,"area":null},{"id":"2512.05394","title":"Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability","created":"2025-12-05","cited_by_count":11,"area":"diffusion"},{"id":"2503.03708","title":"Rethinking Video Tokenization: A Conditioned Diffusion-based Approach","created":"2025-03-05","cited_by_count":9,"area":"diffusion"},{"id":"2506.07136","title":"MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding","created":"2025-06-08","cited_by_count":9,"area":null},{"id":"2503.14070","title":"Fast Autoregressive Video Generation with Diagonal Decoding","created":"2025-03-18","cited_by_count":8,"area":"inference"},{"id":"2509.05441","title":"Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details","created":"2025-09-05","cited_by_count":7,"area":null},{"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":"2604.15911","title":"Efficient Video Diffusion Models: Advancements and Challenges","created":"2026-04-17","cited_by_count":7,"area":"diffusion"},{"id":"2507.15690","title":"DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting","created":"2025-07-21","cited_by_count":6,"area":null},{"id":"2606.17742","title":"BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics","created":"2026-06-16","cited_by_count":5,"area":null},{"id":"2501.05442","title":"Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces","created":"2025-01-09","cited_by_count":4,"area":"diffusion"},{"id":"2504.15661","title":"DiTPainter: Efficient Video Inpainting with Diffusion Transformers","created":"2025-04-22","cited_by_count":4,"area":"diffusion"},{"id":"2505.21205","title":"EF-VI: Enhancing End-Frame Injection for Video Inbetweening","created":"2025-05-27","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":"2601.17124","title":"iFSQ: Improving FSQ for Image Generation with 1 Line of Code","created":"2026-01-23","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":"2503.08665","title":"REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder","created":"2025-03-11","cited_by_count":3,"area":"diffusion"},{"id":"2508.09857","title":"OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better","created":"2025-08-13","cited_by_count":3,"area":"mllm"},{"id":"2511.16957","title":"MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2602.04220","title":"Adaptive 1D Video Diffusion Autoencoder","created":"2026-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2606.21781","title":"Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence","created":"2026-06-19","cited_by_count":3,"area":null},{"id":"2607.06173","title":"MobileWan: Closing the Quality Gap for Mobile Video Diffusion","created":"2026-07-07","cited_by_count":3,"area":"diffusion"},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2604.16479","title":"Latent-Compressed Variational Autoencoder for Video Diffusion Models","created":"2026-04-12","cited_by_count":2,"area":"diffusion"},{"id":"2605.31204","title":"Probabilistic Precipitation Nowcasting with Rectified Flow Transformers","created":"2026-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2605.31590","title":"TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation","created":"2026-05-29","cited_by_count":2,"area":"diffusion"},{"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":"2412.17346","title":"FFA Sora, video generation as fundus fluorescein angiography simulator","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2603.17812","title":"ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation","created":"2026-03-18","cited_by_count":1,"area":"diffusion"},{"id":"2605.30893","title":"Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.30811","title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.14898","title":"FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers","created":"2026-07-16","cited_by_count":1,"area":"diffusion"},{"id":"2608.05798","title":"KVAE: Family of Tokenizers for Multimodal Generative Models","created":"2026-08-06","cited_by_count":1,"area":"diffusion"},{"id":"2609.12874","title":"VideoTok4D: A 4D-Aware Video Tokenizer for Compact World Representation","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2412.04452","title":"Factorized Video Autoencoders for Efficient Generative Modelling","created":"2024-12-05","cited_by_count":0,"area":null},{"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":"2603.14536","title":"Distilling Latent Manifolds: Resolution Extrapolation by Variational Autoencoders","created":"2026-03-15","cited_by_count":0,"area":"distill"},{"id":"2605.02134","title":"Video Generation with Predictive Latents","created":"2026-05-04","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":"2605.15684","title":"ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices","created":"2026-05-15","cited_by_count":0,"area":"diffusion"},{"id":"2608.07569","title":"Latent-Frequency Validity: Fast Spectral Editing with Screened Video-VAE Transfer Operators","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.24293","title":"Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation","created":"2026-08-25","cited_by_count":0,"area":"diffusion"},{"id":"2609.33100","title":"Octree-based Video Representation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.10524","title":"GRACE: Generation-aware latent compression for efficient video generation","created":"2026-10-07","cited_by_count":0,"area":"diffusion"},{"id":"2610.12843","title":"APEX: Asynchronous Prefix Denoising for Extreme Compression","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16204","title":"VGGA: Geometry-Grounded Autoencoder for Video Generation","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}