Metraipolis › archive › dc_642bfec3b707

Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks — arXiv:2609.31862

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31862
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:29.474Z
SHA-256 of the archived text
598ea368acdc33095675c8f817d53956d2fb820155b0511188795562edaf2706
Stable URL of this page
https://metraipolis.com/documento/dc_642bfec3b707

How to cite

Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks — arXiv:2609.31862 — arXiv (en), https://arxiv.org/abs/2609.31862 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_642bfec3b707 (Metraipolis archive dc_642bfec3b707, sha256 598ea368acdc33095675c8f817d53956d2fb820155b0511188795562edaf2706)
BibTeX
@misc{dc642bfec3b707,
  title = {Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks — arXiv:2609.31862},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31862},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_642bfec3b707; sha256 598ea368acdc33095675c8f817d53956d2fb820155b0511188795562edaf2706},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31862. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstruction and simulation at a collider experiment are long chains of specialised algorithms, each tuned to a single step. We explore how one model can serve many of those steps at once, while still producing the intermediate objects (tracks, calorimeter cells, clusters, particles and jets) that make the chain interpretable. To do so, we represent every object in a jet in a single shared token vocabulary and train one model to map any subset of these modalities to any other. A task is then only a choice of which modalities to provide and which to request: particle flow, detector simulation and charged energy subtraction are all directions through the same set of weights. We train over all modality combinations, with a decoder emitting tokens either autoregressively or in parallel. With tokenisation, both architectures train stably with little tuning. In evaluations, both models produce realistic reconstruction and simulation objects, with the autoregressive model particularly faithful to output from Geant4. The autoregressive model also outperforms a state-of-the-art particle flow algorithm on many typical jet reconstruction metrics.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: High Energy Physics - Phenomenology (hep-ph) ; Machine Learning (cs.LG); High Energy Physics - Experiment (hep-ex); Data Analysis, Statistics and Probability (physics.data-an).
Pagina del lavoro: https://arxiv.org/abs/2609.31862 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:28.549Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).