---
slug: "self-supervised-virtual-metrology-for-cmp-mrr-pr-239d239b"
title: "Self-Supervised Virtual Metrology For CMP MRR Prediction (SUTD, A*STAR, NUS)"
headline: "Self-Supervised Virtual Metrology For CMP MRR Prediction (SUTD, A*STAR, NUS)"
canonical: "https://silinex.xyz/wire/self-supervised-virtual-metrology-for-cmp-mrr-pr-239d239b"
date_published: "2026-11-17T00:56:29.000+00:00"
date_modified: "2026-11-17T04:21:54.891+00:00"
author: "Semiconductor Engineering"
publisher: "Silicon Nexus"
category: "chips"
summary: "According to public reporting via Semiconductor Engineering, researchers at Singapore University of Technology and Design (SUTD), A*STAR, and National University of Singapore (NUS) published “Self-Supervised Attention…"
signal_type: "other"
impact_score: 0
tldr:
  - "Researchers at Singapore University of Technology and Design (SUTD), A*STAR, and National University of Singapore (NUS) published “Self-S…"
  - "GREP learns temporal representations from unlabeled sensor signals through global proxy-target regression,... » read more The post appear…"
  - "The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, a…"
entities:
  []
key_metrics:
  []
key_facts:
  - "Researchers at Singapore University of Technology and Design (SUTD), A*STAR, and National University of Singapore (NUS) published “Self-S…"
  - "GREP learns temporal representations from unlabeled sensor signals through global proxy-target regression,... » read more The post appear…"
  - "The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, a…"
---
# Self-Supervised Virtual Metrology For CMP MRR Prediction (SUTD, A*STAR, NUS)

## Silicon TL;DR

1. Researchers at Singapore University of Technology and Design (SUTD), A*STAR, and National University of Singapore (NUS) published “Self-S…
2. GREP learns temporal representations from unlabeled sensor signals through global proxy-target regression,... » read more The post appear…
3. The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, a…

## Wire brief

According to public reporting via Semiconductor Engineering, researchers at Singapore University of Technology and Design (SUTD), A*STAR, and National University of Singapore (NUS) published “Self-Supervised Attention-Based Virtual Metrology for CMP MRR Prediction.” Excerpt “In this paper, we propose Global Regression Pretraining (GREP), a self-supervised, attention-based framework for CMP* MRR prediction.

In related context, gREP learns temporal representations from unlabeled sensor signals through global proxy-target regression,... » read more The post appeared first on Semiconductor Engineering . The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, and temporal process drift. “ *chemical mechanical planarization Find the technical paper here.

Reporting also notes that rico, Jonathan Adam, Nagarajan Raghavan, and Senthilnath Jayavelu. License CC BY-NC-ND 4.0. Tags: A*Star advanced process control chemical mechanical planarization CMP machine learning material removal rate MRR National University of Singapore NUS semiconductor manufacturing Singapore University of Technology and Design SUTD virtual metrology Leave a Reply Cancel reply Comment * Name * (Note: This name will be displayed publicly) Email * (This will not be displayed publicly) Notify me of follow-up comments by email. Ware on Neural Network Model Quantization On Mobile Zack63 on Change Is Tough Yağız Boz on EDA/SIP Revenue Up 12.7%; APAC Roars Back Murugavel Ganesan on Executive Outlook: Agentic AI’s Impact On Chip Design F.

Points still worth watching: Chen on Mask Economics Shape High-NA EUV Adoption B.S. 2 Peter Ateshian on Detect, Diagnose, And Debug Using Sensors And Functional Monitoring Dr.

---

Source desk: **Semiconductor Engineering** · [origin link](https://semiengineering.com/self-supervised-virtual-metrology-for-cmp-mrr-prediction-sutd-astar-nus/)
