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 135 篇，第 1 / 3 页

1. ICLR 20263D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation
2. ICLR 2026AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
3. ICLR 2026AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
4. ICLR 2026Arbitrary-Shaped Image Generation via Spherical Neural Field Diffusion
5. ICLR 2026AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models
6. ICLR 2026AudioX: A Unified Framework for Anything-to-Audio Generation
7. ICLR 2026Aurelius: Relation Aware Text-to-Audio Generation At Scale
8. ICLR 2026Captain Cinema: Towards Short Movie Generation
9. ICLR 2026CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter
10. ICLR 2026CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration
11. ICLR 2026CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation
12. ICLR 2026Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer
13. ICLR 2026ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation
14. ICLR 2026Continuous Audio Language Models
15. ICLR 2026Deep Global-sense Hard-negative Discriminative Generation Hashing for Cross-modal Retrieval
16. ICLR 2026DVD-Quant: Data-free Video Diffusion Transformers Quantization
17. ICLR 2026Evolving Graph Structured Programs for Circuit Generation with Large Language Models
18. ICLR 2026FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
19. ICLR 2026FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates
20. ICLR 2026Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for One-/Two-step High-Fidelity Audio Generation
21. ICLR 2026From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
22. ICLR 2026Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
23. ICLR 2026InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
24. ICLR 2026JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
25. ICLR 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
26. ICLR 2026Latent Fourier Transform
27. ICLR 2026Learning Self-Critiquing Mechanisms for Region-Guided Chest X-Ray Report Generation
28. ICLR 2026LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
29. ICLR 2026LLM2Fx-Tools: Tool Calling for Music Post-Production
30. ICLR 2026LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
31. ICLR 2026MAPSS: Manifold-based Assessment of Perceptual Source Separation
32. ICLR 2026MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control
33. ICLR 2026Mixture of Contexts for Long Video Generation
34. ICLR 2026Motion-Aligned Word Embeddings for Text-to-Motion Generation
35. ICLR 2026P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark
36. ICLR 2026PACE: Pretrained Audio Continual Learning
37. ICLR 2026Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
38. ICLR 2026Plan then Act: Bi-level CAD Command Sequence Generation
39. ICLR 2026Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale
40. ICLR 2026QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
41. ICLR 2026QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
42. ICLR 2026ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation
43. ICLR 2026ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
44. ICLR 2026Rethinking Radiology Report Generation: From Narrative Flow to Topic-Guided Findings
45. ICLR 2026ROGA: Scaling Generalist Agents for Office Productivity Tasks via Tool Generation
46. ICLR 2026SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
47. ICLR 2026SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation
48. ICLR 2026SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation
49. ICLR 2026Steering Autoregressive Music Generation with Recursive Feature Machines
50. ICLR 2026Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers

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。