{"total":24,"rows":[{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80,"area":null},{"id":"2401.15687","title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","created":"2024-01-28","cited_by_count":39,"area":null},{"id":"2509.03883","title":"Human Motion Video Generation: A Survey","created":"2025-09-04","cited_by_count":25,"area":null},{"id":"2512.03520","title":"FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation","created":"2025-12-03","cited_by_count":16,"area":null},{"id":"2606.26740","title":"LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing","created":"2026-06-25","cited_by_count":15,"area":null},{"id":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2511.22989","title":"MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation","created":"2025-11-28","cited_by_count":9,"area":null},{"id":"2512.06065","title":"EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing","created":"2025-12-05","cited_by_count":8,"area":null},{"id":"2608.01771","title":"LiveLight: Real-time Streaming Video Relighting with Interactive Control","created":"2026-08-03","cited_by_count":7,"area":null},{"id":"2502.07556","title":"SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2404.11280","title":"Image Generative Semantic Communication with Multi-Modal Similarity Estimation for Resource-Limited Networks","created":"2024-04-17","cited_by_count":3,"area":null},{"id":"2405.20032","title":"Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2512.16670","title":"FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2406.04873","title":"Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2511.18701","title":"ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2602.03529","title":"Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.05811","title":"Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.06989","title":"Generative Phomosaic with Structure-Aligned and Personalized Diffusion","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2607.28144","title":"ReGenVC: End-to-End Real-Time Generative Video Coding at Ultra-Low Bitrate","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2606.30968","title":"PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.27123","title":"EditaLive! Unified Character Video Editing for Live Streaming","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.03512","title":"ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.20137","title":"StreamErase: Towards Ultra-Fast Streaming Video Erasing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}