Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization

• URL: http://arxiv.org/abs/2606.02434v1
• Date: Mon, 01 Jun 2026 16:06:20 GMT
• Title: Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
• Abstract summary: We propose a visual program synthesis framework in which a Vision-Language Model (VLM) converts inspection images into editable Domain-Specific Language () code describing circuit geometries.<n>Because the VLM is trained solely on synthetic DSL-rendered data, a domain gap arises when processing real Scanning Electron Microscope (SEM) images.<n>We bridge this gap with an input binarization strategy that strips SEM-specific texture and noise, letting the model focus on geometric structure.
• Score: 4.275696286826178
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Precise parametric control over circuit geometry is essential for semiconductor inspection, yet obtaining sufficient real training data remains costly. Although generative models such as diffusion models and Generative Adversarial Networks (GANs) can augment training data, they cannot guarantee the nanometer-scale geometric accuracy required for metrology tasks. We propose a visual program synthesis framework in which a Vision-Language Model (VLM) converts inspection images into editable Domain-Specific Language (DSL) code describing circuit geometries, enabling controlled generation of training data with exact parameter manipulation. Because the VLM is trained solely on synthetic DSL-rendered data, a domain gap arises when processing real Scanning Electron Microscope (SEM) images. We bridge this gap with an input binarization strategy that strips SEM-specific texture and noise, letting the model focus on geometric structure. On the MIIC dataset, binarized inputs improve the mean Dice coefficient from 0.4393 to 0.5256 over the raw-input baseline, demonstrating that simple texture abstraction substantially mitigates the sim-to-real gap.

Related papers

• An Integrated Hardware-Software Design for Low-Data Spatial Defect Detection in Robotic Visual Inspection with Hybrid Optoelectronic Neural Networks [3.2389332471084935]
  This paper proposes a hardware-software integrated optoelectronic architecture to address data overload and inefficient shape-level annotation in visual inspection.<n>A non-imaging, low-data paradigm is established to minimize annotation dependency.<n>Results show that, compared to traditional imaging, the proposed architecture maintains equivalent accuracy while reducing data volume by 90%.
  arXiv  Detail & Related papers  (2026-06-24T01:28:31Z)
• Buffer-Parameterized Machine Learning Surrogate Models for Cross-Technology Signal Integrity Analysis and Optimization [0.0]
  Signal integrity (SI) analysis in printed circuit board interconnects faces increasing complexity.<n> Existing machine learning (ML) surrogate models for predicting SI metrics rely on fixed buffer parameters.<n>This paper introduces a buffer- parameterized ML surrogate modeling methodology capable of handling cross-technology variations without retraining.
  arXiv  Detail & Related papers  (2026-05-18T10:12:57Z)
• SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series [1.6138291258655066]
  Current machine learning approaches for HPC and its telemetry rely on a static subset of anonymous, fixed-position sensor variables tailored to single tasks.<n>We propose SeT-Diff, the first foundational model for compute node telemetry and time-series.<n> Experiments on a real-world supercomputer dataset demonstrate a Mean Absolute Error (MAE) of 0.0470 on reconstruction tasks.
  arXiv  Detail & Related papers  (2026-05-11T00:43:50Z)
• Physics Informed Generative AI Enabling Labour Free Segmentation For Microscopy Analysis [3.3176565054468714]
  This paper introduces a novel framework for labour-free segmentation that successfully bridges the simulation-to-reality gap.<n>We employ a Cycle-Consistent Generative Adversarial Network (CycleGAN) for unpaired image-to-image translation.<n>A U-Net model, trained exclusively on this synthetic data, demonstrated remarkable generalisation when deployed on unseen experimental images.
  arXiv  Detail & Related papers  (2026-02-02T06:36:06Z)
• Improving the Generalisation of Learned Reconstruction Frameworks [1.0026496861838445]
  In X-ray Computed Tomography (CT), convolutional neural networks (CNNs) are widely used to filter the projection data.<n>We propose a hybrid neural network architecture that leverages both graph and grid convolutions to process tomographic data.<n>We demonstrate that GLM outperforms CNNs when performance is quantified in terms of structural similarity and peak signal-to-noise ratio.
  arXiv  Detail & Related papers  (2025-11-16T18:57:13Z)
• TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics [53.442362491589726]
  We present TIGeR (Tool-Integrated Geometric Reasoning), a novel framework that transforms Vision-Language Models (VLMs) into geometric computers.<n>Rather than attempting to internalize complex geometric operations within neural networks, TIGeR empowers models to recognize geometric reasoning requirements.<n>We show that TIGeR achieves SOTA performance on geometric reasoning benchmarks while demonstrating centimeter-level precision in real-world robotic manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-08T16:20:23Z)
• Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces [1.7706010980924418]
  We show that an LLM can learn the physical relationships needed for spectral prediction and inverse design.<n>This "chat-to-chip" workflow represents a step toward more user-friendly data-driven nanophotonics.
  arXiv  Detail & Related papers  (2025-09-29T02:24:57Z)
• Private Training & Data Generation by Clustering Embeddings [74.00687214400021]
  Differential privacy (DP) provides a robust framework for protecting individual data.<n>We introduce a novel principled method for DP synthetic image embedding generation.<n> Empirically, a simple two-layer neural network trained on synthetically generated embeddings achieves state-of-the-art (SOTA) classification accuracy.
  arXiv  Detail & Related papers  (2025-06-20T00:17:14Z)
• Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection [84.52197307286681]
  We propose a novel multitask auto encoding transformation (MAET) model to enhance object detection in a dark environment. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation. We have achieved the state-of-the-art performance using synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-05-06T16:27:14Z)
• Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design [68.1682448368636]
  We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
  arXiv  Detail & Related papers  (2022-03-29T21:18:47Z)
• Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation [75.59415852802958]
  Shape-My-Face (SMF) is a powerful encoder-decoder architecture based on an improved point cloud encoder, a novel visual attention mechanism, graph convolutional decoders with skip connections, and a specialized mouth model. Our model provides topologically-sound meshes with minimal supervision, offers faster training time, has orders of magnitude fewer trainable parameters, is more robust to noise, and can generalize to previously unseen datasets.
  arXiv  Detail & Related papers  (2020-12-16T20:02:36Z)
• One-step regression and classification with crosspoint resistive memory arrays [62.997667081978825]
  High speed, low energy computing machines are in demand to enable real-time artificial intelligence at the edge. One-step learning is supported by simulations of the prediction of the cost of a house in Boston and the training of a 2-layer neural network for MNIST digit recognition. Results are all obtained in one computational step, thanks to the physical, parallel, and analog computing within the crosspoint array.
  arXiv  Detail & Related papers  (2020-05-05T08:00:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.