论文解读
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
音乐生成 | 7.0/10
音乐生成
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
会议任务专题
ICLR 2026 - 音乐生成
共 9 篇 ICLR 2026 音乐生成 方向论文
论文解读
Latent Fourier Transform
音乐生成 | 8.5/10
论文解读
SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation
音乐生成 | 8.5/10
论文解读
Steering Autoregressive Music Generation with Recursive Feature Machines
音乐生成 | 8.5/10
论文解读
SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
音乐生成 | 7.5/10
论文解读
Token-Based Audio Inpainting via Discrete Diffusion
音乐生成 | 7.5/10
论文解读
YuE: Scaling Open Foundation Models for Long-Form Music Generation
音乐生成 | 7.5/10
论文解读
AudioX: A Unified Framework for Anything-to-Audio Generation
音频生成 | 7.5/10
论文解读
Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
音乐生成 | 8.5/10
论文解读
Continuous Audio Language Models
音频生成 音乐生成 | 9.5/10
论文解读
Discovering and Steering Interpretable Concepts in Large Generative Music Models
音乐生成 | 7.5/10
论文解读
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
音乐生成 | 8.0/10
论文解读
Latent Fourier Transform
音乐生成 | 7.5/10
论文解读
SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation
音乐生成 | 7.0/10
论文解读
Steering Autoregressive Music Generation with Recursive Feature Machines
音乐生成 | 8.0/10
论文解读
SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
音乐生成 | 7.5/10
论文解读
Token-Based Audio Inpainting via Discrete Diffusion
音频生成 | 7.5/10
论文解读
YuE: Scaling Open Foundation Models for Long-Form Music Generation
音乐生成 | 7.5/10
论文解读
A Generative-First Neural Audio Autoencoder
音乐生成 | 8.5/10