Miguel Aguilar

Aptiv

• CODAI 2022: Embedded AI Challenges in Perception Systems

Samira Ahmadifarsani

Technical University of Munich

• CODAI 2023: Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM’s UMA

Maximilian Bartel

Roofline.ai

• CODAI 2026: Heterogeneous Execution of Accelerators Using IREE

Hadjer Benmeziane

Ecole Nationale Supérieure d’Informatique / Université Polytechnique Hauts-de-France

• CODAI 2022: HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices

Endri Bezati

Huawei Zurich Research Center

• CODAI 2023: ART: An Actor Transition Systems RunTime for Enabling Efficient Partitioning of Neural Network Graphs

Oliver Bringmann

University of Tübingen

• CODAI 2022: Integration of a Systolic Array Based Hardware Accelerator into a DNN Operator Auto-Tuning Framework

• CODAI 2026: AI Compilers @ Uni Tübingen

Jeronimo Castrillon

TU Dresden

• CODAI 2023: Next-generation Compilers for Emerging Systems

• CODAI 2026: Compilers for In-Memory Computing Systems

Tianqi Chen

Carnegie Mellon University / NVIDIA

• CODAI 2022: Abstract for Machine Learning Compilations

• CODAI 2026: Building ML Systems Foundations at the Age of AI

Matheus Ferraz

Osnabrück University

• CODAI 2023: Pros and Cons of Executable Neural Networks for Deeply Embedded Systems

Birte Friesel

Osnabrück University

• CODAI 2023: Pros and Cons of Executable Neural Networks for Deeply Embedded Systems

Perry Gibson

Fractile

• CODAI 2026: The Compiler Before The Horse: Design Space Exploration at Fractile

Kailash Gopalakrishnan

EnCharge AI

• CODAI 2022: The Past, Presence and Future of AI Compute Platforms

Tobias Grosser

University of Cambridge

• CODAI 2025: Quidditch: An End-to-End Deep Learning Compiler for Occamy using IREE & xDSL

Liyuan Guo

TU Dresden

• CODAI 2022: Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

Pavol Jancura

NXP Semiconductors / Eindhoven University of Technology

• CODAI 2023: Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

Matthias Jobst

TU Dresden

• CODAI 2022: Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

Jan Moritz Joseph

Roofline.ai

• CODAI 2025: Roofline’s Flexible Deployment Solution to Compile for GPUs, CPUs, and NPUs in Edge-AI Systems

Florian Kelber

TU Dresden

• CODAI 2022: Performance Models and Energy-Optimal Mapping of DNNs on Many-Core Hardware with Dynamic Power Management

Philipp van Kempen

Technical University of Munich

• CODAI 2022: MLonMCU: TinyML Benchmarking with Fast Retargeting

• CODAI 2023: Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM’s UMA

Fredrik Kjolstad

Stanford University

• CODAI 2023: Software and Hardware for Sparse ML

Akash Kumar

Technical University of Munich

• CODAI 2023: Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

Zhaoying Li

National University of Singapore

• CODAI 2023: Accelerating Edge AI with Morpher: An Integrated Design, Compilation and Simulation Framework for CGRAs

Chen Liu

TU Dresden

• CODAI 2022: Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

Yao Lu

NXP Semiconductors / Eindhoven University of Technology

• CODAI 2023: Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

Christian Mayr

TU Dresden

• CODAI 2022: Performance Models and Energy-Optimal Mapping of DNNs on Many-Core Hardware with Dynamic Power Management

• CODAI 2022: Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

Lotfi Abdelkrim Mecharbat

Ecole Nationale Supérieure d’Informatique / Université Polytechnique Hauts-de-France

• CODAI 2022: HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices

Tulika Mitra

National University of Singapore

• CODAI 2023: Accelerating Edge AI with Morpher: An Integrated Design, Compilation and Simulation Framework for CGRAs

Daniel Müller-Gritschneder

Technical University of Munich / TU Wien

• CODAI 2022: MLonMCU: TinyML Benchmarking with Fast Retargeting

• CODAI 2023: Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM’s UMA

• CODAI 2026: Graph-Level Tiling, Operator Patching, and Fusion for Distributed, Memory-Optimized, and Fault-Tolerant TinyML Deployment

Stephen Neuendorffer

AMD

• CODAI 2025: MLIR-based Programming for Spatial Architectures

Smail Niar

Université Polytechnique Hauts-de-France / INSA Hauts-de-France / CNRS

• CODAI 2022: HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices

• CODAI 2026: Hardware-Aware AI: Bridging Model Design, Compilers, and Edge Deployment

Julius Ott

Technical University of Munich

• CODAI 2023: Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

Hamza Ouarnoughi

Ecole Nationale Supérieure d’Informatique / Université Polytechnique Hauts-de-France

• CODAI 2022: HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices

Johannes Partzsch

TU Dresden

• CODAI 2022: Performance Models and Energy-Optimal Mapping of DNNs on Many-Core Hardware with Dynamic Power Management

• CODAI 2022: Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

Federico Nicolás Peccia

FZI Research Center for Information Technology

• CODAI 2022: Integration of a Systolic Array Based Hardware Accelerator into a DNN Operator Auto-Tuning Framework

Thomas Pfeil

Recogni

• CODAI 2023: Hardware-Aware Network Compression: From Data to Silicon

Andrew Reusch

OctoML

• CODAI 2022: Whole-model Optimization with Apache TVM

Moritz Riesterer

NXP Semiconductors

• CODAI 2026

Hiram Rayo Torres Rodriguez

NXP Semiconductors / Eindhoven University of Technology

• CODAI 2023: Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

Fouad Sakr

Aptiv

• CODAI 2023: Tiny Machine Learning: Enabling Intelligence on Constrained Devices

Ananda Samajdar

IBM Research

• CODAI 2025: Co-optimizing Algorithms, Hardware and Software for AI Acceleration: IBM Perspective

Ulf Schlichtmann

Technical University of Munich

• CODAI 2022: MLonMCU: TinyML Benchmarking with Fast Retargeting

• CODAI 2023: Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM’s UMA

Lorenzo Servadei

Technical University of Munich / Infineon

• CODAI 2023: Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

Xinyue Shi

TU Dresden

• CODAI 2022: Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

Iryna de Albuquerque Silva

CEA

• CODAI 2026: Aidge: The Collaborative and Open Source Platform for Edge AI

Sean Silva

EnCharge AI

• CODAI 2025: Practical Discrepancies in AI Performance

Lukas Sommer

Codeplay

• CODAI 2023: SYCL – A Modern C++ Programming Model for Accelerators

Olaf Spinczyk

Osnabrück University

• CODAI 2023: Pros and Cons of Executable Neural Networks for Deeply Embedded Systems

Max Sponner

Technical University of Munich / Infineon

• CODAI 2023: Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

Rafael Stahl

Technical University of Munich

• CODAI 2022: MLonMCU: TinyML Benchmarking with Fast Retargeting

• CODAI 2023: Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM’s UMA

Nick van de Waterlaat

NXP Semiconductors / Eindhoven University of Technology

• CODAI 2023: Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

Sebastian Vogel

NXP Semiconductors

• CODAI 2022: Conclusion

• CODAI 2023: Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge

Bernhard Vogginger

TU Dresden

• CODAI 2022: Performance Models and Energy-Optimal Mapping of DNNs on Many-Core Hardware with Dynamic Power Management

Bernd Waschneck

Infineon

• CODAI 2023: Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

Dhananjaya Wijerathne

National University of Singapore

• CODAI 2023: Accelerating Edge AI with Morpher: An Integrated Design, Compilation and Simulation Framework for CGRAs

Robert Wille

Technical University of Munich

• CODAI 2023: Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing

Maxim Zaks

Mojo Community

• CODAI 2026: Solving the Multi-Platform Problem with Mojo

Jiang Zhang

Huawei

• CODAI 2026: Hardware-Affine Compiler Ecosystem Optimization for Ascend