ExploreNet2 min read
ExploreNet: Learning Where to Explore in Diffusion GRPO
Group-relative RL methods such as Flow-GRPO post-train image generators by exploring with isotropic Gaussian noise added at every denoising step. This noise decides which rollouts the model learns from, yet it perturbs every channel and spatial position of the latent equally.
By Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov, Luke ZettlemoyerarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Oct 1, 2026.
Comments
Sign in to join the discussion.