When Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-Tuning
arXiv:2610.28849v1 Announce Type: new Abstract: Latent diffusion models almost universally place a Gaussian prior on the VAE latent space. For base generation this default is unproblematic; under reinforcement-learning fine-tuning, however, it carries a structural limitation. The standard VAE's KL…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.LG
When Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-Tuning