Jedat Inc. · TSE:3841
Jedat — Pollen Metrology — Technical Presentation (December 2025)
36 slides from Jedat's technical presentation, Dec 2, 2025
Slide 1: Collaborative AI for Next-Gen Semi Manufacturing - A Software Platform Revolution
Webinar #1 Collaborative AI for Next-Gen Semi Manufacturing - A Software Platform Revolution 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 1
Slide 2: Webinar #1 – Agenda
Webinar #1 – Agenda Duration: 1 hour Collaborative AI for Next-Gen Semi Manufacturing A Software Platform Revolution 40min Introduction to Collaborative AI and the six categories of AI used in industrial environments Overview of how “hardware + software + data intelligence” defines the next generati
Slide 3: 1. Context of Collaborative AI in Semiconductor Industry
1. Context of Collaborative AI in Semiconductor Industry 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 3
Slide 4: Semiconductor Fab Software Stack
Semiconductor Fab Software Stack Five main layers YMS Yield Analytics Yield Management System ADC Data quality & Defect Intelligence Automatic Defect Classification MES Fab Orchestration Manufacturing Exec. System FDC SPC R2R Control Fault Detection & Statistical Process Stability and Quality of the
Slide 5: Artificial Intelligence is paving the way to a new process control paradigm
Artificial Intelligence is paving the way to a new process control paradigm Accelerate process development and maximize yield with a scalable solution Hardware + Software + Data Intelligence 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 5
Slide 6: Different types of AI
Different types of AI Focused on Semiconductor, Scalable Across Material Science Industries Industrial Need AI Technology Key Benefits Examples Real-time analytics of Breaks silos, boosts Collaborate across teams Collaborative AI SEM, TEM, Optical (…) images productivity and process data Detect know
Slide 7: Collaborative AI: The Central Platform That Orchestrates All AI Technologies
Collaborative AI: The Central Platform That Orchestrates All AI Technologies Although each AI technology brings specific value - supervised, unsupervised, generative, agent, explainable, and collaborative - none of them can deliver deep impact at fab scale in isolation. To be effective inside a semi
Slide 8: Collaborative AI: Implementation of multiple complementary AI technologies
Implementation of multiple complementary AI technologies The sixth software layer — an AI orchestration layer above MES, YMS, ADC, and control systems. YMS SOFTWARE PLATFORM Yield Management System COLLABORATIVE AI ADC Automatic Defect Classification MES Manufacturing Exec. System FDC SPC R2R Contro
Slide 9: Collaborative AI: Implementation of multiple complementary AI technologies
Implementation of multiple complementary AI technologies The sixth software layer — an AI orchestration layer above MES, YMS, ADC, and control systems. This architecture allows any AI - internal or external - to plug in seamlessly, guaranteeing openness and eliminating black-box SOFTWARE PLATFORM de
Slide 10: Few words on Pollen
Few words on Pollen Collaborative AI Process Control Software Platform for Next-Gen Manufacturing Bridging Data Silos in Material Science with • Who we are – More than 10 years development Collaborative AI for Yield Enhancement Founded in 2014, Pollen is a software company based in Grenoble, France,
Slide 11: 2. Industry challenges and AI
2. Industry challenges and AI 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 11
Slide 12: Problems to solve
Problems to solve Focused on Semiconductor, Scalable Across Material Science Industries Time-pressure - Long R&D-to-production cycles - Costly expert time (engineers, data scientists) Process complexity - Nonlinear design with nanometer-scale materials - Demanding process control Disjointed workflow
Slide 13: Time-pressure
Time-pressure Automated analysis and comprehensive reports Time-pressure • Long R&D-to-production cycles Automated and customized analysis • Costly expert time (engineers, data scientists) • Improved analytics • Faster time to result • More insights from the process Automated and customised analysis
Slide 14: Process complexity
Process complexity Centralized platform Process complexity - Nonlinear design with nanometer-scale materials - Demanding process control Cloud Tools Split analysis AI Tools Big data Tools Heterogeneous results Statistics Tools Multiple tool learning Computer Vision Tools Varied infrastructure Centra
Slide 15: Disjointed workflows
Disjointed workflows Open platform Disjointed workflows - Poor synergy between teams - Tools and data remain siloed R&D Process Data Science R&D R&D Process Metrology Data Science Tools Tools Tools Tools Tools 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 15
Slide 16: Disjointed workflows
Disjointed workflows Open platform Disjointed workflows - Poor synergy between teams SDK to leverage internal IP - Tools and data remain siloed R&D Process Data Science R&D R&D Process Metrology Data Science Tools Tools Tools Tools Tools Open platform (Software Development Kit) • Customized analytic
Slide 17: Low ROI from data
Low ROI from data Collaborative AI to support process experts Low ROI from data - Data underused, scattered - Hard to scale insights ROI R&D Process Table data Tools Image Data Production Metrology Tools Cloud Point Spectral Data Data Science Data Science Time Series Tools 12/2/2025 POLLEN WEBINAR O
Slide 18: Low ROI from data
Low ROI from data Collaborative AI to support process experts Low ROI from data - Data underused, scattered - Hard to scale insights Image Data Table data R&D Process Tools Production Metrology Cloud Point ROI Tools Data Science Data Science Spectral Data Tools Time Series Collaborative AI • Create
Slide 19: Confidentiality
Confidentiality Industrial data is sensitive Confidentiality of data - Data contains IP from Industries Proposition - Cloud solutions rely on trust On-Premise Solution SOLUTION CLOUD Solutions ON-PREMISE Clear data Full control over data Uncontrolled Secured data access Potential usage of confidenti
Slide 20: Pollen solution with Collaborative AI platform
Pollen solution with Collaborative AI platform Focused on Semiconductor, Scalable Across Material Science Industries Proposition Time-pressure - Long R&D-to-production cycles Bridging Data Silos in Material Science with Collaborative AI - Costly expert time (engineers, data scientists) Process compl
Slide 21: 3. Smart3 Software Platform
3. Smart3 Software Platform 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 21
Slide 22: Comprehensive Smart3 Software Suite to Boost the Production of Semiconductor Devices
Comprehensive Smart3 Software Suite to Boost the Production of Semiconductor Devices Metrology Inspection Process Optimization Software Development Kit 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 22
Slide 23: Who are the users of collaborative AI Platform?
Who are the users of collaborative AI Platform? • IC Makers Fabs • Fabless • Process Tool Suppliers • Metrology/Inspection Tool Suppliers 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 23 23
Slide 24: Yield Optimization for Fabs and Fabless
Yield Optimization for Fabs and Fabless A unique & unified framework to optimize processes Wafers/Chips from Internal Processes and Foundries FABLESS Faster Device Selection A Model Training and Best recipes & Run to Optimization Evaluation Run optimization Faster Process Selection FOUNDRIES & FABS
Slide 25: Yield Optimization for Tool Suppliers
Yield Optimization for Tool Suppliers A unique & unified framework to provide full flexibility and capabilities Process Control & Process Tools connected to Process Yield Challenges IC FABS & FOUNDRIES New process control capabilities Daily customization Best recipes & Run to Run optimization Applic
Slide 26: 4. Use Cases & Demo
4. Use Cases & Demo 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 26
Slide 27: Demo plan
Demo plan 1. Collaborative Platform, example SAM implementation 2. Turnkey solution for Metrology 3. Turnkey solution for Inspection 4. Collaborative Workflow Strategy 5. Implementation for HVM 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 27
Slide 28: 1- Collaborative Platform
1- Collaborative Platform Plugin Manager Ease of use internal library to customize Smart3 platform without any software developement https://youtu.be/UJ0uPbH8o_c 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 28
Slide 29: 2- Turnkey solution for Metrology
2- Turnkey solution for Metrology Process # Yield Process 1 Process 2 YIELD ENHANCEMENT Slant 2D Meta-structure TopDown CDSEM TopDown CDSEM Analysis can be: • CNN, R-CNN Computing • Third Party softwares • Internal Software Code Post computing AEI Metrology User results database ADI Metrology 3D Ana
Slide 30: 3- Turnkey solution for Inspection
3- Turnkey solution for Inspection Process # Yield THERMAL EPITAXY TREATMENT YIELD ENHANCEMENT Slip Lines Analysis can be: PWG* Computing • CNN, R-CNN • Third Party softwares • Internal Software Code Post computing User results database Analysis VM Wafer measurement Defined Context Images Epitaxy pr
Slide 31: 4- Collaborative Workflow Strategy
4- Collaborative Workflow Strategy SmartOEM3: Collaborative AI at the Service of Supplier IP Wavefront Phase Imaging https://wooptix.com/ Atomic Force Microscope https://www.infinitesima.com/ 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 31
Slide 32: 5- Implemention for HVM
5- Implemention for HVM Use the API 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 32
Slide 33: 5. Next Webinars, Q&A
5. Next Webinars, Q&A 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 33
Slide 34: Next Webinars
Next Webinars Webinar 1 – Dec 2 (2025): Collaborative AI for Next-Gen Semi Manufacturing - A Software Platform Revolution 2026 – Q1 Webinar 2: Build Internal Applications 10× Faster - The AI-Native Software Platform & SDK SmartOEM3 Webinar 3: AI-Driven Metrology: From Data Fusion to Real-Time Proces
Slide 35: Any question?
Any question? Seminar slides access , please send an email to johann.foucher@pollen-metrology.com 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 35
Slide 36: Thank you
Thank you 12/2/2025 POLLEN WEBINAR ON COLLABORATIVE AI 36
Pollen Metrology — Technical Presentation (December 2025) on 6ix