{"total":49,"rows":[{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105,"area":null},{"id":"2405.11616","title":"Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention","created":"2024-05-19","cited_by_count":100,"area":null},{"id":"2504.07963","title":"PixelFlow: Pixel-Space Generative Models with Flow","created":"2025-04-10","cited_by_count":97,"area":null},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91,"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":"2501.04689","title":"SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images","created":"2025-01-08","cited_by_count":42,"area":null},{"id":"2307.04751","title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","created":"2023-07-10","cited_by_count":29,"area":null},{"id":"2406.04542","title":"M&M VTO: Multi-Garment Virtual Try-On and Editing","created":"2024-06-06","cited_by_count":29,"area":null},{"id":"2405.04682","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","created":"2024-05-07","cited_by_count":25,"area":null},{"id":"2305.12689","title":"FIT: Far-reaching Interleaved Transformers","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2410.04081","title":"Epsilon-VAE: Denoising as Visual Decoding","created":"2024-10-05","cited_by_count":16,"area":null},{"id":"2504.07940","title":"Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos","created":"2025-04-10","cited_by_count":16,"area":null},{"id":"2502.02300","title":"Density Ratio Estimation with Conditional Probability Paths","created":"2025-02-04","cited_by_count":13,"area":null},{"id":"2312.05915","title":"Diffusion for Natural Image Matting","created":"2023-12-10","cited_by_count":11,"area":null},{"id":"2601.10909","title":"FrankenMotion: Part-level Human Motion Generation and Composition","created":"2026-01-15","cited_by_count":10,"area":null},{"id":"2504.14264","title":"Generative emulation of chaotic dynamics with coherent prior","created":"2025-04-19","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":"2602.18647","title":"Noise Scheduling as Information-Guided Allocation in Diffusion Training","created":"2026-02-20","cited_by_count":7,"area":null},{"id":"2403.08277","title":"VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition","created":"2024-03-13","cited_by_count":5,"area":null},{"id":"2405.07157","title":"Semi-Self-Supervised Domain Adaptation: Developing Deep Learning Models with Limited Annotated Data for Wheat Head Segmentation","created":"2024-05-12","cited_by_count":5,"area":null},{"id":"2408.16046","title":"Scaling Up Diffusion and Flow-based XGBoost Models","created":"2024-08-28","cited_by_count":5,"area":null},{"id":"2305.18900","title":"One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2404.09051","title":"Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2411.16668","title":"Diffusion Features for Zero-Shot 6DoF Object Pose Estimation","created":"2024-11-25","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":"2307.00868","title":"MADS: Modulated Auto-Decoding SIREN for time series imputation","created":"2023-07-03","cited_by_count":3,"area":null},{"id":"2412.08149","title":"AsyncDSB: Schedule-Asynchronous Diffusion Schr\\\"odinger Bridge for Image Inpainting","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2502.02187","title":"ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2311.08745","title":"Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2507.17800","title":"Improving Multislice Electron Ptychography with a Generative Prior","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2605.18749","title":"WavFlow: Audio Generation in Waveform Space","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2408.10119","title":"Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2504.05977","title":"Diffusion Based Ambiguous Image Segmentation","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2504.17525","title":"Text-to-Image Alignment in Denoising-Based Models through Step Selection","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2602.05360","title":"Breaking Semantic Hegemony: Decoupling Principal and Residual Subspaces for Generalized OOD Detection","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.18792","title":"Rethinking Uncertainty Quantification and Entanglement in Image Segmentation","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.16126","title":"Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\\\"odinger Samplers","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.26032","title":"Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2407.18290","title":"Several questions of visual generation in 2024","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2504.21368","title":"Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2506.19834","title":"A standard transformer and attention with linear biases for molecular conformer generation","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2511.18078","title":"Diffusion-based Surrogate Model for Time-varying Underwater Acoustic Channels","created":"2025-11-22","cited_by_count":0,"area":null},{"id":"2601.02881","title":"Towards Agnostic and Holistic Universal Image Segmentation with Bit Diffusion","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2607.05325","title":"CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.09811","title":"Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.25716","title":"FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}