LithoWorld: An Endpoint World Model for Lithography Process-Window Recovery

Botong Zhao; Fang Yu; Xinyuan Chen; Yue Lu

cs.CVOct 16, 2026

LithoWorld: An Endpoint World Model for Lithography Process-Window Recovery

Authors: Botong Zhao, Fang Yu, Xinyuan Chen, Yue Lu

Organizations: Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China

Abstract

Lithography process drift can move a fabricated pattern outside its process window, producing unqualified scanning electron microscopy (SEM) morphology. We present LithoWorld, an endpoint world model for SEM-guided parameter recovery. Interior representative targets jointly determine qualified reference appearance and correction supervision. A causal predictive branch aligns currentimage features with endpoint representations, while a conditional flow policy generates a two-dimensional correction as an action chunk. The model learns from 173 groups of measured SEMs organized as focus-exposure maps, preserving unmeasured cells as unknown. On 200 test pairs from the 73-group subset, LithoWorld achieves 88.5% qualified-region success and 46.0% interior success, exceeding the strongest comparison method by 2.5 and 6.0 percentage points, respectively. Ablations separate the effects of target selection, endpoint alignment, and output parameterization. Qualitative SEM retrieval illustrates recovery to qualified interiors without requiring exact reference-coordinate matching.

Figures & tables

Figure 1: LithoWorld. A shared frozen encoder supplies current/reference SEM tokens to a causal Qwen backbone. Current hidden states predict the qualified endpoint representation through an MLP, with stop-gradient reference features as supervision. Action hidden states, current parameters, and noisy actions condition the DiT expert. Dashed alignment paths are training-only. The reference is selected from an observed process-window interior where available; its coordinates and the full FEM label map are excluded from policy inputs.

Method	SEM-73 (%)			SEM-100 (%)		SEM-73 margin
	GSR $\uparrow$	ISR $\uparrow$	Macro $\uparrow$	GSR $\uparrow$	ISR $\uparrow$	(grid) $\uparrow$
DINOv2 + MLP	80.0 $\pm$ 1.0	26.5 $\pm$ 2.0	80.1 $\pm$ 5.1	79.2 $\pm$ 0.5	23.1 $\pm$ 0.6	0.54 $\pm$ 0.02
ACT-goal	83.0 $\pm$ 1.5	33.5 $\pm$ 1.0	86.8 $\pm$ 2.5	82.6 $\pm$ 0.7	26.9 $\pm$ 0.9	0.65 $\pm$ 0.02
Diffusion Policy-goal	85.0 $\pm$ 1.0	38.0 $\pm$ 1.5	86.1 $\pm$ 2.3	84.7 $\pm$ 0.8	29.5 $\pm$ 0.9	0.72 $\pm$ 0.02
MDT-image	84.0 $\pm$ 1.0	35.5 $\pm$ 1.0	84.1 $\pm$ 1.9	83.9 $\pm$ 0.7	28.0 $\pm$ 0.9	0.69 $\pm$ 0.01
ManiFlow-goal	86.0 $\pm$ 1.5	40.0 $\pm$ 1.0	86.6 $\pm$ 3.0	86.4 $\pm$ 0.8	31.6 $\pm$ 0.6	0.78 $\pm$ 0.00

Table 1: Comparison on the FEM dataset using a common frozen DINOv2 encoder. Results are mean

\pm

sample standard deviation over three runs. GSR: qualified-region success; ISR: interior success; Macro: group-macro GSR. Rates are percentages; mean margin is in grid units, with zero assigned to failures.

Figure 2: Offline SEM recovery at checkpoint 15,000. Existing SEMs at nearest-grid cells $q$ are shown for S0/S4/S8 of the eight predicted increments. R/G denote source qualification labels. Blue paths show continuous predictions $p$ , hollow circles show $q$ , and purple stars mark input references; dark green is the observed core and gray is unmeasured. The reference is an input (the same SEM as S8 in (a)). These curated successes use FEM lookup, not newly acquired closed-loop observations; SEM-73 GSR is 89.0%.

Target	Align.	GSR (%)	ISR (%)	Margin
Nearest	Off	82.5 $\pm$ 1.0	13.0 $\pm$ 1.0	0.43 $\pm$ 0.02
Nearest	On	84.5 $\pm$ 1.5	16.0 $\pm$ 1.5	0.48 $\pm$ 0.01
Interior	Off	85.5 $\pm$ 1.0	41.5 $\pm$ 1.0	0.81 $\pm$ 0.02
Interior	On	88.5 $\pm$ 1.0	46.0 $\pm$ 1.0	0.94 $\pm$ 0.01

Table 2: Target construction and endpoint alignment on SEM-73. Changing targets changes both reference SEMs and action labels. Rates are percentages; margin is in grid units.

Variant	GSR (%)	ISR (%)
LithoWorld (ours)	88.5 $\pm$ 1.0	46.0 $\pm$ 1.0
$H=1$ , same backbone	88.0 $\pm$ 1.5	45.0 $\pm$ 2.0
Small fusion replaces Qwen	85.5 $\pm$ 1.5	41.0 $\pm$ 1.0
SEM-73-only training	86.5 $\pm$ 1.5	43.0 $\pm$ 1.5
SEM-100-only training	74.5 $\pm$ 1.5	30.0 $\pm$ 2.0
Without reference image	77.0 $\pm$ 1.0	31.0 $\pm$ 1.0

Table 3: Output, backbone, and training-data controls evaluated on SEM-73.

H=1

keeps the same backbone and predicts the total correction. Other rows change one factor.

Semiconductor Manufacturing

Semiconductor manufacturing uses process engineering, metrology, and automation to make chips reliably, improve yield, and meet tight device requirements.

See all 45 papers

LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography
Jun 25, 2026Yuqi Jiang, Yumeng Liu, Zimu Li +7World Model Learning Semiconductor Manufacturing
Zhejiang University, No. 38 Zheda Road, Xihu District, Hangzhou, Zhejiang Province, China.
Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection
Jun 8, 2026Pangyun Jeong, Jiyeong Kong, Yuehua Hu +2Vision-Language Models VLM Adaptation
1HYU-KITECH Joint Department, Hanyang University, Ansan, 15588, Korea · 4Korea Institute of Industrial Technology, Ansan, 15588, Korea · 2Micro/Nano System Department, Korea University, Seoul 02841, Korea +1
Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning
Feb 22, 2026Haoyu Yang, Haoxing RenInverse Design
NVIDIA Corp. Austin, TX, USA

Jun 25, 2026J/K move · Enter open · S save

LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography

Yuqi Jiang, Yumeng Liu, Zimu Li, Jinyuan Deng+6

Zhejiang University, No. 38 Zheda Road, Xihu District, Hangzhou, Zhejiang Province, China.

World Model Learning Semiconductor Manufacturing Physics-Informed ML Inverse Design

Open paper AskPDF arXiv

As semiconductor technology nodes scale, computational lithography is essential for ensuring yield and performance. However, lithography is a continuous physical process involving mask optimization, optical imaging, resist exposure, and development, which existing models fail to capture. To overcome this limitation, we present LithoDreamer, the first physics-informed World Model (WM) framework for computational lithography, which formulates the ``Layout-Mask-Resist Image-After Development Image (ADI)'' pipeline as a decision-driven multi-step evolution system. LithoDreamer captures feature changes between adjacent states to model stage-specific physics-informed latent spaces, in which it controls process intervention exploration and drives subsequent state transitions. To achieve interpretable intervention optimization without continuous supervision, we propose a contrastive variational optimization paradigm that contrasts the latent differences between intervention paths with variational evolution constraints, guiding the model to generate evolutions consistent with real lithography physics. Experiments show LithoDreamer achieves state-of-the-art performance in forward evolution and inverse planning. Our lithography dataset is publicly available at GitHub (https://github.com/7jiangyq/lithodreamer.git).

Abstract

Semiconductor Manufacturing

Explore similar work

LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography

Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection

Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning