{"total":20,"rows":[{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111,"area":null},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66,"area":null},{"id":"2403.12933","title":"Zero-Reference Low-Light Enhancement via Physical Quadruple Priors","created":"2024-03-19","cited_by_count":58,"area":null},{"id":"2404.14381","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","created":"2024-04-22","cited_by_count":34,"area":null},{"id":"2410.10076","title":"VideoAgent: Self-Improving Video Generation","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2404.15909","title":"Learning Long-form Video Prior via Generative Pre-Training","created":"2024-04-24","cited_by_count":8,"area":null},{"id":"2311.16635","title":"MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2510.26412","title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2503.15655","title":"R$^2$: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2307.16371","title":"MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2605.28035","title":"MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2512.22780","title":"Plug In, Grade Right: Psychology-Inspired AGIQA","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2602.02630","title":"Trailer Reimagined: An Innovative, Llm-DRiven, Expressive Automated Movie Summary framework (TRAILDREAMS)","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2402.15746","title":"Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2608.01780","title":"Investigating Social Bias in Narrative Image Generation","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2610.00097","title":"DramaAgent: Agentic Storytelling Video Generation","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}