collaborators

8 papers

hep-ph2026

A Scientific Human-Agent Reproduction Pipeline

Joschka Birk, Gregor Kasieczka, Siddharth Mishra-Sharma +3

Reproducing scientific analyses is essential for preserving knowledge, building extensible codebases, and deepening researcher understanding - yet the effort often outweighs its ac…

hep-ph2026

Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives

Ibrahim Elsharkawy, Joschka Birk, Vinicius Mikuni +3

Foundation models (FMs) trained on large datasets and fine-tuned on downstream tasks have emerged as a powerful paradigm in AI for science. Industrial FMs are typically trained usi…

physics.ins-det2026

SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation

Joschka Birk, Frank Gaede, Anna Hallin +3

We introduce SPADE (SPlit And Delay Embeddings), an autoregressive transformer for sequences whose tokens carry multiple features. Rather than embedding these features jointly, SPA…

hep-ph2025

Enhancing next token prediction based pre-training for jet foundation models

Joschka Birk, Anna Hallin, Gregor Kasieczka +3

Next token prediction is an attractive pre-training task for jet foundation models, in that it is simulation free and enables excellent generative capabilities that can transfer ac…

hep-ph2025

Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics

Oz Amram, Luca Anzalone, Joschka Birk +7

Foundation models are deep learning models pre-trained on large amounts of data which are capable of generalizing to multiple datasets and/or downstream tasks. This work demonstrat…

hep-ph2025

OmniJet-: Learning point cloud calorimeter simulations using generative transformers

Joschka Birk, Frank Gaede, Anna Hallin +3

We show the first use of generative transformers for generating calorimeter showers as point clouds in a high-granularity calorimeter. Using the tokenizer and generative part of th…