Research map / Image generation / Autoregressive and latent generation
Latent Fourier Transform
Mason Long Wang, Cheng-Zhi Anna Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use latent-spectrum conditioning (LatentFT-MLP) vs best baseline ILVR | diffusion autoencoder · MTG-Jamendo conditional generation | FAD: 1.061 -> 0.337 | Improved |
| use LatentFT-MLP vs ILVR | diffusion autoencoder · MTG-Jamendo conditional generation | loudness correlation: 0.575 -> 0.815 | Improved |
| use LatentFT vs ILVR for blending | diffusion autoencoder · MTG-Jamendo blending | timbre MCD/100: 0.825 -> 1.021 | Hurt |
| use LatentFT-UNet vs ILVR for blending | diffusion autoencoder · MTG-Jamendo blending | FAD: 2.696 -> 1.357 | Improved |
| add random frequency masking during training (ablation) | LatentFT-MLP · MTG-Jamendo conditional generation | FAD: 5.341 -> 0.349 | Improved |
| add correlated bin scores in mask sampling (ablation) | LatentFT-MLP · MTG-Jamendo conditional generation | FAD: 2.744 -> 0.349 | Improved |
| use logarithmic frequency axis for correlation (ablation) | LatentFT-MLP · MTG-Jamendo conditional generation | loudness correlation: 0.512 -> 0.800 | Improved |
| add encoder (ablation) | LatentFT-MLP · MTG-Jamendo conditional generation | loudness correlation: 0.028 -> 0.800 | Improved |
| add bandpass augmentation (ablation) | LatentFT-MLP · MTG-Jamendo conditional generation | FAD: 0.349 -> 1.511 | Hurt |
| train without frequency masking (ablation) | LatentFT-MLP · MTG-Jamendo blending | FAD: 4.789 -> 1.371 | Improved |
| post-hoc latent frequency masking of pretrained DAC/RAVE | DAC, RAVE · MTG-Jamendo conditional generation | FAD: 7.016 (DAC), 4.695 (RAVE) vs 0.337 | Hurt |
Closest papers by meaning
- Fast Timing-Conditioned Latent Audio Diffusion (ICML 2024 · similarity 0.89)
- MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence (NeurIPS 2024 · similarity 0.86)
- MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotion (AAAI 2024 · similarity 0.86)
- MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction (NeurIPS 2025 · similarity 0.86)
- MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models (CVPR 2024 · similarity 0.86)
- MuPT: A Generative Symbolic Music Pretrained Transformer (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
