{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2008.04838","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","created":"2020-08-11","cited_by_count":171},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143},{"id":"2502.05139","title":"Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound","created":"2025-02-07","cited_by_count":137},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"2111.03600","title":"Hybrid Spectrogram and Waveform Source Separation","created":"2021-11-05","cited_by_count":91},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43},{"id":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40},{"id":"2505.07652","title":"ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models","created":"2025-05-12","cited_by_count":38},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35},{"id":"2508.11484","title":"CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models","created":"2025-08-15","cited_by_count":29},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28},{"id":"2407.21658","title":"Beat this! Accurate beat tracking without DBN postprocessing","created":"2024-07-31","cited_by_count":27},{"id":"2601.03655","title":"VideoMemory: Toward Consistent Video Generation via Memory Integration","created":"2026-01-07","cited_by_count":25},{"id":"2512.12372","title":"STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative","created":"2025-12-13","cited_by_count":23},{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20},{"id":"2508.08244","title":"Cut2Next: Generating Next Shot via In-Context Tuning","created":"2025-08-11","cited_by_count":15},{"id":"2511.08521","title":"UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist","created":"2025-11-11","cited_by_count":15},{"id":"2512.11274","title":"FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion","created":"2025-12-12","cited_by_count":10},{"id":"2604.04875","title":"DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing","created":"2026-04-06","cited_by_count":7},{"id":"2603.10256","title":"ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA","created":"2026-03-10","cited_by_count":5}],"next_cursor":null}