Name: Fast Machine Learning for Science Conference 2025
Start: 2025-09-01T08:30:00+02:00
End: 2025-09-05T17:30:00+02:00
Location: ETH Zurich

Fast Machine Learning for Science Conference 2025

from Monday 1 September 2025 (08:30) to Friday 5 September 2025 (17:30)

Monday 1 September 2025

08:30 Registration
Registration
08:30 - 09:00
09:00 Tutorials
09:00 - 12:30
Contributions

09:00 NeuraLUT-Assemble: Hardware-aware Assembling of Sub-Neural Networks for Efficient LUT Inference - Marta Andronic (Imperial College London) Oliver Cassidy (Imperial College London)

09:00 hls4ml - Benjamin Ramhorst (ETH Zurich)

09:00 Part 1: Agile Hardware Design for AI: A Hands-On Tutorial with SODA and Bambu - Giovanni Gozzi (Politecnico di Milano) Michele Fiorito (Politecnico di Milano) Vito Giovanni Castellana (Pacific Northwest National Laboratory) Antonino Tumeo (Pacific Northwest National Laboratory) Fabrizio Ferrandi (Politecnico di Milano)

11:00 Super Neural Architecture Codesign Package (SNAC-Pack) - Dmitri Demler

11:00 Designing and Deploying Low-Latency Neural Networks on FPGAs with HGQ and da4ml - Chang Sun (California Institute of Technology (US))

11:00 Part 2: Agile Hardware Design for AI: A Hands-On Tutorial with SODA and Bambu - Giovanni Gozzi (Politecnico di Milano) Michele Fiorito (Politecnico di Milano) Vito Giovanni Castellana (Pacific Northwest National Laboratory) Antonino Tumeo (Pacific Northwest National Laboratory) Fabrizio Ferrandi (Politecnico di Milano) Nicolo Ghielmetti (CERN)

11:00 Coyote v2: Open-source Abstractions and Infrastructure for FPGAs - Benjamin Ramhorst (ETH Zurich)
12:30 Registration
Registration
12:30 - 13:30

13:30 Social: Welcome
Welcome
13:30 - 14:00
14:00 Invited talks
14:00 - 15:30
Contributions

14:00 Reasoning Language Models: Overview and Blueprint - Maciej Besta (ETH Zurich)

14:45 Real-time mixed-signal electronic circuits for understanding and implementing neural computation - Giacomo Indiveri (ETH Zurich)
15:30 Coffee
Coffee
15:30 - 15:50
15:50 Invited talks
15:50 - 17:20
Contributions

15:50 Real-time inference at the LHC - Vava Gligorov (Centre National de la Recherche Scientifique (FR))

16:35 Real-time inference in gravitational wave astronomy (REMOTE) - Maximilian Dax (ELLIS Institute Tübingen)
17:20 Commute to ETH Main Building (by ETH link 17:34 or 17:54). Meet Polyterrasse
Commute to ETH Main Building (by ETH link 17:34 or 17:54). Meet Polyterrasse
17:20 - 18:00

18:00 Social: Reception
Reception
18:00 - 22:00
Room: Dozentenfoyer
Tuesday 2 September 2025
09:00 Invited talks
09:00 - 10:30
Contributions

09:00 The JAX scientific ecosystem - Patrick Kidger (Cradle.bio)

09:45 Wearable TinyML Platforms for Biosignal Intelligence Across the Body - Andrea Cossettini (ETH Zurich)
10:30 Coffee
Coffee
10:30 - 11:00
11:00 Invited talks
11:00 - 12:00
Contributions

11:00 Real-time ML and neuromorphic computing for smart robots - Yulia Sandamirskaya (Zurich University of Applied Sciences)
12:00 Lunch
Lunch
12:00 - 13:00
13:00 Contributed talks
13:00 - 15:00
Contributions

13:00 FINN+: Towards Hassle-Free Co-Design of FPGA DNN Inference Accelerators - Felix Jentzsch

13:20 End-to-End Neural Network Compression and Deployment for Hardware Acceleration Using PQuant and hls4ml - Roope Oskari Niemi

13:40 PrioriFI: Efficient Fault Injection for Edge Neural Networks - Olivia Weng

14:00 ENABOL: Enabling Neural Backpropagation On-chip Learning for Edge AI Systems - Manuel Valentin (Northwestern University)

14:20 da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs - Chang Sun (California Institute of Technology (US))

14:40 AMD AI-Engines in fixed latency environments - Ioannis Xiotidis (CERN)
15:00 Posters and coffee

15:00 - 16:00
16:00 Contributed talks
16:00 - 17:40
Contributions

16:00 Balancing Prediction Performance, Transparency and Energy Consumption in Machine Learning Models for Data Streams - Kirsten Köbschall

16:20 Arbolta: A Fault Tolerance Study using Minimal Hardware Simulation - Alexander Redding (UC San Diego)

16:40 SuperSONIC: Cloud-Native Infrastructure for ML Inferencing - Yuan-Tang Chou (University of Washington (US))

17:00 Embedding domain knowledge: Inductive biases for algorithmic alignment in Machine Learning - Serio Angelo Maria Agriesti (Department of Technology, Management and Economics, Technical University of Denmark, Lyngby, Denmark)

17:20 Pushing Matrix-Vector Multiplication Performance on AMD AI Engines for Low-Latency Edge Inference - Dimitrios Danopoulos (CERN)
Wednesday 3 September 2025
09:00 Invited talks
09:00 - 10:30
Contributions

09:00 The Instrumental Edge: Real-Time and AI-Ready Scientific Discovery - Adam Thompson (NVIDIA)

09:45 AI for next-gen cellular networks (6G) - Bozidar Radunovic (Microsoft Research)
10:30 Coffee
Coffee
10:30 - 11:00
11:00 Invited talks
11:00 - 11:45
Contributions

11:00 Next Generation GPU Signal Processing Pipeline for Radio Astronomy - Luigi Cruz (SETI)
11:45 Conference photo outside of auditorium!
Conference photo outside of auditorium!
11:45 - 12:00

12:00 Lunch
Lunch
12:00 - 13:00
13:00 Contributed talks
13:00 - 15:00
Contributions

13:00 Real-Time Anomaly Detection in the CMS Level-1 Trigger with AXOL1TL - Sabrina Giorgetti (Universita e INFN, Padova (IT))

13:20 GELATO: A Generic Event-Level Anomaly detection Trigger for ATLAS - Kenny Jia (Stanford University/ SLAC)

13:40 Advancing the CMS Level-1 Trigger: Jet Tagging with DeepSets at the HL-LHC - Christopher Edward Brown (CERN)

14:00 Low-Latency On-Chip Tau Event Selection with Machine Learning for the Belle II Level-1 Trigger - Deven Misra (University of Tokyo)

14:20 Accelerated Graph Neural Network Inference on FPGAs for Real-Time Muon Triggering at the HL-LHC - Davide Fiacco (Sapienza Universita e INFN, Roma I (IT))

14:40 Jet finding in real-time using an object detection CNN - Leon Bozianu (Universite de Geneve (CH))
15:00 Posters and coffee

15:00 - 16:00
16:00 Contributed talks
16:00 - 17:40
Contributions

16:00 KAN-LUT: Efficient LUT-Based Acceleration of Kolomogorov-Arnold Networks (KANs) on FPGAs - Duc Hoang (Massachusetts Inst. of Technology (US))

16:20 COLLIDE-2V - 750 Million Dual-View LHC Event Dataset for Low-Latency ML - Eric Anton Moreno (Massachusetts Institute of Technology (US))

16:40 Accelerating Efficient Transformer Architectures for Point Cloud Data using hls4ml (REMOTE) - Jan-Frederik Schulte (Purdue University (US))

17:00 Hierarchical Dataflow Accelerator of Interaction Networks for Large-Scale Particle Tracking on FPGA - Bo-Cheng Lai

17:20 An ML Pipeline for Real-time Gravitational Wave Alerts - Christina Reissel (Massachusetts Inst. of Technology (US)) Katya Govorkova (Massachusetts Inst. of Technology (US)) Philip Coleman Harris (Massachusetts Inst. of Technology (US))
17:40 Map to Tessin Grotto
Map to Tessin Grotto
17:40 - 17:45

17:45 Walk to Tessin Grotto (see map)
Walk to Tessin Grotto (see map)
17:45 - 18:00

18:00 Social: Conference Dinner
Conference Dinner
18:00 - 23:00
Thursday 4 September 2025
09:30 Invited talks
09:30 - 11:00
Contributions

09:30 Scaling up Advanced, Near-Sensor AI: An Open Platform Approach - Luca Benini (ETH Zurich)

10:15 Co-Design for Efficient & Adaptive ML - Yaman Umuroglu (AMD)
11:00 Coffee
Coffee
11:00 - 11:30
11:30 Contributed talks: Contributed talks
Contributed talks
11:30 - 12:40
Contributions

11:30 Towards a Self-Driving Trigger: Adaptive Response in Real Time - Giovanna Salvi (University of Michigan (US))

11:50 Easing the path to deployment in ML4Sys through FPGAs - Maximilian Heer (ETH Zurich)

12:10 Go small then go home - hyperparameter transfer for ML in HEP - Liv Helen Vage (Princeton University (US))

12:30 Edge Deep Learning for Particle Physics (EPIGRAPHY) - Benedikt Maier (Imperial College (GB))
12:40 Fast ML foundation discussion
Fast ML foundation discussion
12:40 - 13:30

Lunch
Lunch
12:40 - 13:30
13:30 Contributed talks
13:30 - 15:30
Contributions

13:30 Low-Latency Resource-Efficient GNNs for Jet Tagging on FPGAs - Zhiqiang (Walkie) Que (Imperial College London)

13:50 Smartpixels: Intelligent pixel detectors: Towards a radiation hard ASIC with on-chip machine learning in 28nm CMOS - Benjamin Weiss (Cornell University) Jannicke Pearkes (University of Colorado Boulder (US))

14:10 Quantum-Inspired Tensor Network Models for Ultrafast Jet Tagging on FPGAs - Ema Puljak (universitat Autònoma de Barcelona)

14:30 Toward a Ultra-Fast, Energy-Efficient Readout of Calorimeters with Neuromorphic Processing - Enrico Lupi (CERN, INFN Padova (IT))

14:50 SparsePixels: Efficient Convolution for Sparse Data on FPGAs - Ho-Fung Tsoi (University of Pennsylvania)

15:10 FPGA-accelerated ML for real-time RHEED inference - Abdelrahman Asem Elabd (University of Washington (US))
15:30 Coffee
Coffee
15:30 - 16:00
16:00 Contributed talks: Contributed talks
Contributed talks
16:00 - 17:00
Contributions

16:00 Low-latency Jet Tagging for HL-LHC Using Transformer Architectures - Lauri Antti Olavi Laatu (Imperial College (GB))

16:20 Radiation-Hard, ML-Based, Low-Latency Compression for the LHCb ECAL Upgrade - Katya Govorkova (Massachusetts Inst. of Technology (US))

16:40 Chisel4ml: Using Chisel For Direct Circuit Implementation of Deeply Quantized Neural Networks - Jure Vreča
17:00 Birds-of-a-Feather
17:00 - 18:00
Contributions

17:00 MLOps Pipeline for Continuous Deployment of Machine Learning Algorithms for HEP - Maciej Mikolaj Glowacki (CERN) Marius Köppel (ETH Zurich (CH))

17:00 QONNX Birds-of-a-Feather (BoF) Session - Yaman Umuroglu
Friday 5 September 2025
09:00 Invited talks
09:00 - 09:45
Contributions

09:00 Fast inference with Decision Forests - Richard Stotz (Google Zurich)

09:20 Efficient Graph neural networks at Google - Mathieu Guillame-Bert (Google Zurich)
09:45 Coffee
Coffee
09:45 - 10:15
10:15 Contributed talks
10:15 - 11:16
Contributions

10:15 A Real-Time GNN-based Clustering Algorithm for the Level 1 Calorimeter Trigger at Belle II - Isabel Haide (Karlsruhe Institute for Technology)

10:35 Experiences Deploying a Hybrid PVFinder Algorithm for Primary Vertex Reconstruction in LHCb’s GPU-Resident HLT1 - Mohamed Elashri (University of Cincinnati)

10:55 State space models for Project 8 event reconstruction - Hannah Binney

11:15 Get your poster!
11:15 Invited talks: Summary talk and poster prizes
Summary talk and poster prizes
11:15 - 12:35
Contributions

11:16 Conference summary - Nhan Tran (Fermi National Accelerator Lab. (US))

11:55 Poster prizes and closing - Benjamin Ramhorst (ETH Zurich) Denis-Patrick Odagiu (ETH Zurich (CH)) Marius Köppel (ETH Zurich (CH))
14:00 Satellite event: hls4ml dev meeting - Jan-Frederik Schulte (Purdue University (US)) Benjamin Ramhorst (ETH Zurich)
Satellite event: hls4ml dev meeting
- Jan-Frederik Schulte (Purdue University (US))
- Benjamin Ramhorst (ETH Zurich)
14:00 - 15:00
For minutes of the discussion, see https://indico.cern.ch/event/1586270/

Choose timezone