{"list":"other","total":52,"rows":[{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"id":"2404.07724","title":"Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models","created":"2024-04-11","cited_by_count":254},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"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":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"2504.05741","title":"DDT: Decoupled Diffusion Transformer","created":"2025-04-08","cited_by_count":109},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87},{"id":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2411.10061","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","created":"2024-11-15","cited_by_count":72},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48},{"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":"2205.15439","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","created":"2022-05-30","cited_by_count":33},{"id":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30},{"id":"2505.21448","title":"OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers","created":"2025-05-27","cited_by_count":27},{"id":"2412.15191","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","created":"2024-12-19","cited_by_count":22},{"id":"2402.12636","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing","created":"2024-02-20","cited_by_count":21},{"id":"2409.17550","title":"A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation","created":"2024-09-26","cited_by_count":19},{"id":"2412.08988","title":"EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing","created":"2024-12-12","cited_by_count":17},{"id":"2508.00733","title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","created":"2025-08-01","cited_by_count":12},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11},{"id":"2506.14742","title":"SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting","created":"2025-06-17","cited_by_count":9},{"id":"2312.05412","title":"CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional Modeling","created":"2023-12-08","cited_by_count":7},{"id":"2505.01263","title":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","created":"2025-05-02","cited_by_count":6}],"next_cursor":null}