30 July 2026 to 5 August 2026
Natal, Brazil
America/Sao_Paulo timezone

PanopTag: Simultaneously Tagging All Jets in a Particle Collision Event

Not scheduled
20m
Natal, Brazil

Natal, Brazil

Via Costeira Sen. Dinarte Medeiros Mariz, 6664-6704 - Ponta Negra, Natal - RN, 59090-002
Talk Artificial Intelligence, Machine Learning and Quantum Computing in HEP

Speaker

Umar Sohail Qureshi (Stanford University)

Description

Jet tagging, identifying the origin of jets produced in particle collisions, is a critical classification task in high-energy physics. Despite the revolutionary impact of deep learning on jet tagging over the past decade, the paradigm has remained unchanged. In particular, jets are classified independently, one at a time. This single-jet approach ignores correlations, overlaps, and wider event context between jets. We introduce \textsc{PanopTag}, a new paradigm for jet tagging that departs from traditional single-jet tagging approaches. Rather than classifying jets independently, \textsc{PanopTag} simultaneously tags all jets by employing an encoder-decoder architecture that uses jet kinematics as queries to cross-attend to particle flow object embeddings. We evaluate \textsc{PanopTag} on heavy-flavor $(b/c)$-tagging and demonstrate remarkable performance improvements over state-of-the-art single-jet baselines that are only accessible by exploiting event-level features and correlations between jets.

I read the instructions above Yes

Authors

Umar Sohail Qureshi (Stanford University) Dr Brendon Bullard (SLAC National Accelerator Laboratory) Ariel Gustavo Schwartzman (SLAC National Accelerator Laboratory (US))

Presentation materials

There are no materials yet.