Research map / Image generation / Autoregressive and latent generation
PluGeN: Multi-Label Conditional Generation from Pre-trained Models
Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka, Maciej Zieba, Patryk Wielopolski, Rafał Kurczab, Marek Smieja
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 PluGeN instead of StyleFlow | StyleGAN2 · FFHQ attribute manipulation | Average Acc: 0.86 -> 0.90 | Improved |
| use PluGeN instead of StyleFlow | StyleGAN2 · FFHQ attribute manipulation | Average FID: 32.59 -> 46.51 | Hurt |
| use PluGeN instead of cFlow | VAE · CelebA independent conditional generation | F1: 0.29 -> 0.44 | Improved |
| use PluGeN instead of cFlow | VAE · CelebA test-set attribute combinations | F1: 0.49 -> 0.69 | Improved |
| replace NICE with CNF (ablation) | PluGeN with VAE · CelebA test-set attribute combinations | F1: 0.69 -> 0.63 | Hurt |
| replace NICE with CNF (ablation) | PluGeN with VAE · CelebA test-set attribute combinations | FID: 72.72 -> 68.96 | Improved |
| replace NICE with CNF (ablation) | PluGeN with VAE · CelebA independent conditional generation | F1: 0.44 -> 0.41 | Hurt |
| replace NICE with CNF (ablation) | PluGeN with VAE · CelebA independent conditional generation | FID: 77.48 -> 73.31 | Improved |
| increase β from 1 to 8 (ablation) | PluGeN with β-VAE · CelebA generation | FID: 55.11 -> 77.94 | Hurt |
| increase β from 1 to 8 (ablation) | PluGeN with β-VAE · CelebA generation | F1: 0.66 -> 0.57 | Hurt |
Closest papers by meaning
- Molecule Design by Latent Prompt Transformer (NeurIPS 2024 · similarity 0.86)
- TFG-Flow: Training-free Guidance in Multimodal Generative Flow (ICLR 2025 · similarity 0.84)
- Geometric Representation Condition Improves Equivariant Molecule Generation (ICML 2025 · similarity 0.84)
- Linear combinations of latents in generative models: subspaces and beyond (ICLR 2025 · similarity 0.84)
- Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation (AAAI 2025 · similarity 0.84)
- Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation (NeurIPS 2025 · similarity 0.84)
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.
