{"list":"other","total":57,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2302.00482","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","created":"2023-02-01","cited_by_count":879},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"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":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"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":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2406.18009","title":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","created":"2024-06-26","cited_by_count":152},{"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":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90},{"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":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"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":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61},{"id":"2506.00045","title":"ACE-Step: A Step Towards Music Generation Foundation Model","created":"2025-05-28","cited_by_count":56},{"id":"2406.07686","title":"AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation","created":"2024-06-11","cited_by_count":41},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40},{"id":"2506.13053","title":"ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching","created":"2025-06-16","cited_by_count":30},{"id":"2412.15220","title":"SyncFlow: Toward Temporally Aligned Joint Audio-Video Generation from Text","created":"2024-12-03","cited_by_count":26},{"id":"2505.10793","title":"SongEval: A Benchmark Dataset for Song Aesthetics Evaluation","created":"2025-05-16","cited_by_count":26},{"id":"2405.17842","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","created":"2024-05-28","cited_by_count":23},{"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":"2507.12890","title":"DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization","created":"2025-07-17","cited_by_count":12},{"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":"2307.15484","title":"Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding","created":"2023-07-28","cited_by_count":10},{"id":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10},{"id":"2309.00424","title":"Learning Speech Representation From Contrastive Token-Acoustic Pretraining","created":"2023-09-01","cited_by_count":9},{"id":"2512.14291","title":"GLM-TTS Technical Report","created":"2025-12-16","cited_by_count":9},{"id":"2408.05758","title":"VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing","created":"2024-08-11","cited_by_count":7},{"id":"2512.19090","title":"JoyVoice: Long-Context Conditioning for Anthropomorphic Multi-Speaker Conversational Synthesis","created":"2025-12-22","cited_by_count":7},{"id":"2211.09495","title":"Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation","created":"2022-11-17","cited_by_count":6},{"id":"2309.15512","title":"High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models","created":"2023-09-27","cited_by_count":6},{"id":"2512.04720","title":"M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesis","created":"2025-12-04","cited_by_count":6},{"id":"2508.02849","title":"SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec","created":"2025-08-04","cited_by_count":5},{"id":"2511.18487","title":"InstructAudio: Unified speech and music generation with natural language instruction","created":"2025-11-23","cited_by_count":5},{"id":"2508.20088","title":"AudioStory: Generating Long-Form Narrative Audio with Large Language Models","created":"2025-08-27","cited_by_count":3},{"id":"2512.09504","title":"DMP-TTS: Disentangled multi-modal Prompting for Controllable Text-to-Speech with Chained Guidance","created":"2025-12-10","cited_by_count":3}],"next_cursor":null}