{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"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":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"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":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"2503.05639","title":"VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control","created":"2025-03-07","cited_by_count":84},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2402.10009","title":"Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion","created":"2024-02-15","cited_by_count":60},{"id":"1905.09773","title":"Speech2Face: Learning the Face Behind a Voice","created":"2019-05-23","cited_by_count":55},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46},{"id":"2410.00741","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","created":"2024-10-01","cited_by_count":41},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35},{"id":"2509.17818","title":"ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment","created":"2025-09-22","cited_by_count":27},{"id":"2305.13050","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","created":"2023-05-22","cited_by_count":22},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20},{"id":"2508.19320","title":"MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation","created":"2025-08-26","cited_by_count":19},{"id":"2504.08296","title":"Generative AI for Film Creation: A Survey of Recent Advances","created":"2025-04-11","cited_by_count":17},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15},{"id":"2304.06818","title":"Soundini: Sound-Guided Diffusion for Natural Video Editing","created":"2023-04-13","cited_by_count":14},{"id":"2503.20782","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","created":"2025-03-26","cited_by_count":14},{"id":"2510.00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model","created":"2025-09-27","cited_by_count":14},{"id":"2102.04680","title":"Tr\\\"aumerAI: Dreaming Music with StyleGAN","created":"2021-02-09","cited_by_count":11},{"id":"2308.06981","title":"The Sound Demixing Challenge 2023 $\\unicode{x2013}$ Cinematic Demixing Track","created":"2023-08-14","cited_by_count":11},{"id":"2009.08083","title":"Crossing You in Style: Cross-modal Style Transfer from Music to Visual Arts","created":"2020-09-17","cited_by_count":10},{"id":"2509.01596","title":"O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing","created":"2025-09-01","cited_by_count":10},{"id":"2410.21269","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","created":"2024-10-28","cited_by_count":8},{"id":"2104.08189","title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction","created":"2021-04-16","cited_by_count":7},{"id":"2404.16581","title":"AudioScenic: Audio-Driven Video Scene Editing","created":"2024-04-25","cited_by_count":5},{"id":"2309.02405","title":"Generating Realistic Images from In-the-wild Sounds","created":"2023-09-05","cited_by_count":4},{"id":"2411.16199","title":"VIRES: Video Instance Repainting via Sketch and Text Guided Generation","created":"2024-11-25","cited_by_count":2}],"next_cursor":null}