AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching

Yao Lai, Xuyuan Xiong, Zeyue Xue, Guojin Chen, Jing Wang, Xihui Liu, Rui Zhang, Robert D. Mullins, Bei Yu, Ping Luo

ICML 2026 · Reinforcement learning › RL from feedback · approach: RL fine-tuning of generative models · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add GRPO RL fine-tuning after SFT (ablation)LithoGRPO · MetalSetShot count: 803 -> 444Improved
add GRPO RL fine-tuning after SFT (ablation)LithoGRPO · ViaSetShot count: 989 -> 398Improved
add GRPO RL fine-tuning after SFT (ablation)LithoGRPO · MetalSetPVB: 40722 -> 39838Improved
add GRPO RL fine-tuning after SFT (ablation)LithoGRPO · MetalSetL2: 29123 -> 28933Improved
add GRPO RL fine-tuning after SFT (ablation)LithoGRPO · ILT average over 4 datasetsaverage rank: 4.7 -> 4.3Improved
add SFT on differentiable metrics after pretraining (ablation)LithoGRPO · MetalSetL2: 32824 -> 29123Improved
add SFT on differentiable metrics after pretraining (ablation)LithoGRPO · MetalSetShot count: 487 -> 803Hurt
use two sampling steps instead of one (ablation)LithoGRPO · Metal layersaverage rank: 4.7 -> 3.8Improved
use ten sampling steps instead of one (ablation)LithoGRPO · Metal layersaverage rank: 4.7 -> 6.7Hurt
use two sampling steps instead of one (ablation)LithoGRPO · Metal layersruntime (s): 0.104 -> 0.203Hurt
use colored noise instead of Gaussian noise in SDE exploration (ablation)LithoGRPO · MetalSetshot countImproved
lower noise level from a=0.1 to a=0.01 (ablation)LithoGRPO · MetalSetreward convergence speedHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy