音频生成论文趋势 2023–2026

主要结论

• 音频生成论文从 2023 年的 32 篇增长到 2026 年的 136 篇，三年间扩大到约 4.3 倍。
• ICLR 是发音频生成论文最多的会议，2023–2026 年共 135 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 16 篇。
• 在「语音与音频」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的视听学习是 1.8 倍，音频生成是 4.3 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
• ICML 2026PHALAR: Phasors for Learned Musical Audio Representations
• ICLR 2026AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
• CVPR 2026AudioStory Generating Long-Form Narrative Audio with Large Language Models
• NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
• ICML 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
• ICLR 2025ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation
• CVPR 2025AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
• NeurIPS 2024Vocal Call Locator Benchmark (VCL) for localizing rodent vocalizations from multi-channel audio
• ICML 2024An Independence-promoting Loss for Music Generation with Language Models
• ICLR 2024Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
• CVPR 2024FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization
• NeurIPS 2023High-Fidelity Audio Compression with Improved RVQGAN
• ICML 2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
• ICLR 2023AudioGen: Textually Guided Audio Generation
• CVPR 2023Conditional Generation of Audio From Video via Foley Analogies
• NeurIPS 2026AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
• ICML 2026SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
• ICLR 2026AudioX: A Unified Framework for Anything-to-Audio Generation
• CVPR 2026Avatar Forcing Real-Time Interactive Head Avatar Generation for Natural Conversation

全部音频生成论文

共 136 篇，第 2 / 3 页

51. ICLR 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
52. ICLR 2026Latent Fourier Transform
53. ICLR 2026Learning Self-Critiquing Mechanisms for Region-Guided Chest X-Ray Report Generation
54. ICLR 2026LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
55. ICLR 2026LLM2Fx-Tools: Tool Calling for Music Post-Production
56. ICLR 2026LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
57. ICLR 2026MAPSS: Manifold-based Assessment of Perceptual Source Separation
58. ICLR 2026MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control
59. ICLR 2026Mixture of Contexts for Long Video Generation
60. ICLR 2026Motion-Aligned Word Embeddings for Text-to-Motion Generation
61. ICLR 2026P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark
62. ICLR 2026PACE: Pretrained Audio Continual Learning
63. ICLR 2026Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
64. ICLR 2026Plan then Act: Bi-level CAD Command Sequence Generation
65. ICLR 2026Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale
66. ICLR 2026QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
67. ICLR 2026QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
68. ICLR 2026ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation
69. ICLR 2026ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
70. ICLR 2026Rethinking Radiology Report Generation: From Narrative Flow to Topic-Guided Findings
71. ICLR 2026ROGA: Scaling Generalist Agents for Office Productivity Tasks via Tool Generation
72. ICLR 2026SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
73. ICLR 2026SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation
74. ICLR 2026SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation
75. ICLR 2026Steering Autoregressive Music Generation with Recursive Feature Machines
76. ICLR 2026Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers
77. ICLR 2026SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
78. ICLR 2026TaskCraft: Automated Generation of Agentic Tasks
79. ICLR 2026Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language Descriptions
80. ICLR 2026Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
81. ICLR 2026Token-Based Audio Inpainting via Discrete Diffusion
82. ICLR 2026Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering
83. ICLR 2026Toward Complex-Valued Neural Networks for Waveform Generation
84. ICLR 2026UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
85. ICLR 2026UniF$^2$ace: A $\underline{Uni}$fied $\underline{F}$ine-grained $\underline{Face}$ Understanding and Generation Model
86. ICLR 2026Unified Multi-Modal Interactive and Reactive 3D Motion Generation via Rectified Flow
87. ICLR 2026UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
88. ICLR 2026Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
89. ICLR 2026VibeVoice: Expressive Podcast Generation with Next-Token Diffusion
90. ICLR 2026YuE: Scaling Open Foundation Models for Long-Form Music Generation
91. ICML 2026AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing
92. ICML 2026AudioMosaic: Contrastive Masked Audio Representation Learning
93. ICML 2026BAT: Better Audio Transformer Guided by Convex Gated Probing
94. ICML 2026BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps
95. ICML 2026Bridging Your Imagination with Audio-Video Generation via a Unified Director
96. ICML 2026CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
97. ICML 2026DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing
98. ICML 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
99. ICML 2026Learning Tight Rejection Boundaries without Negatives for Strict One-Class Audio Deepfake Detection
100. ICML 2026LLM-Guided Loop Bound Generation for Program Termination Verification

常见问题

2023–2026 年四大会议一共有多少篇音频生成论文？

共 357 篇，按年份分别是 2023 年 32 篇、2024 年 73 篇、2025 年 116 篇、2026 年 136 篇。

NeurIPS 2026 有多少篇音频生成论文？

NeurIPS 2026 有 21 篇音频生成论文，上一届是 32 篇。

ICLR 2026 有多少篇音频生成论文？

ICLR 2026 有 64 篇音频生成论文，上一届是 43 篇。

ICML 2026 有多少篇音频生成论文？

ICML 2026 有 25 篇音频生成论文，上一届是 10 篇。

CVPR 2026 有多少篇音频生成论文？

CVPR 2026 有 26 篇音频生成论文，上一届是 31 篇。

哪个会议的音频生成论文最多？

ICLR，2023–2026 年共 135 篇。