pith. sign in

Scaling rectified flow transformers for high-resolution image synthesis

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling

cs.CV · 2026-02-11 · unverdicted · novelty 7.0

DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.

citing papers explorer

Showing 1 of 1 citing paper.

  • Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling cs.CV · 2026-02-11 · unverdicted · none · ref 6

    DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.