GSoC 2025 Projects Related To ML4EP

ML4EP is a project of the CERN SFT group focused on developing common machine learning (ML) software tools to support HEP experiments. The current ongoing activities are:

• Designing generic generative ML models for fast simulation of calorimeter showers
• Developing ML software for efficient inference in C++, such as SOFIE and creating interfaces between external provided ML software and HEP software like ROOT
• Building tools for ML inferfence in FPGA like hls4ml
• Developing common libraries for model compression and quantization, facilitating optimized ML workflow and porting of ML HEP applications in a real time environment.

Project Proposals

• Integrating Support for Google XLS in HLS4ML

• Optimizing Model Splitting in hls4ml for Efficient Multi-Graph Inference

• TMVA SOFIE - GPU Support for Machine Learning Inference

• TMVA SOFIE - HLS4ML Integration for Machine Learning Inference

• TMVA SOFIE - Enhancing Keras Parser and JAX/FLAX Integration