PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
Mixed citations
Aadet al.(ATLAS), Transforming jet flavour tag- ging at ATLAS, Nature Commun.17, 541 (2026), arXiv:2505.19689 [hep-ex]
Mixed citation behavior. Most common role is method (60%).
15
Pith papers citing it
Method
60% of classified citations
citation-role summary
method 3
background 2
citation-polarity summary
representative citing papers
Cell-level Transformers classify collimated ALP photon-jets versus single photons with AUC 0.98 and regress diphoton mass to ~64 MeV, beating shower-shape and other ML baselines in an ATLAS-like GEANT4 simulation.
Simultaneous measurements of b-jet tagging and c-jet mistagging efficiency scale factors for the ATLAS GN2 tagger achieve precisions below 2% and 5% respectively using 56 fb⁻¹ of 13.6 TeV ttbar data.
The GN2 b-jet tagger is calibrated in 56 fb⁻¹ of 13.6 TeV pp data using dileptonic tt̄ events, yielding data-to-simulation scale factors of 0.9–1.3 with ~1% uncertainty in the best bins.
ATLAS measures ttH cross section times BR(H→γγ) at 1.13 SM with 164 fb⁻¹ at 13.6 TeV, sets tH limit at 6.2 SM, and combined with prior data excludes |α|>38° and purely CP-odd coupling at 5.8σ.
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
A DNN tags the hardest FSR jet from leading-jet 4-momenta to correct di-jet invariant mass, improving signal resolution and search sensitivity by over 10% with minimal background distortion across a broad mass range.
A 10 TeV lepton collider using the effective gamma-W to W process could improve m_W precision beyond 10 MeV and extract CKM elements like V_cb with reduced hadronic uncertainties via high-precision hadronic calorimetry and flavor tagging.
Higgs boson cross-section in H→4ℓ measured as 3.65 fb with new LHC data, consistent with SM expectation of 3.68 fb and signal strength 0.99±0.13.
No evidence for charginos and neutralinos in R-parity violating Higgs-decay channels; masses 150-1100 GeV excluded at 95% CL assuming equal lepton branching fractions.
A color-octet scalar Θ pair-produced via gluons and decaying to quark pairs can account for the CMS excess in equal-mass dijet pairs at 0.95 TeV with a 65 fb cross section for the real case.
No significant excess observed in search for X → S(bb)H(γγ); 95% CL limits on σ×BR set from 9 fb to 0.06 fb over m_X 170-1000 GeV and m_S 15-500 GeV in 199 fb^{-1} of ATLAS data.
Updated ATLAS search for HH → bbγγ with 308 fb⁻¹ yields observed μ_HH = 0.9^{+1.4}_{-1.1}, 95% CL limit μ_HH < 3.7, and κ_λ in [-1.6, 6.6].
No excess above Standard Model background is observed; 95% CL limits are set on couplings of the U1 vector leptoquark model for masses 1.5-3.0 TeV.
ATLAS Inner Detector track and vertex reconstruction maintains high efficiency, good resolution, and low fake rates for up to 80 simultaneous proton-proton interactions in Run 2 and Run 3 data and simulations.
citing papers explorer
-
Particle-Lund Multimodality in Jet Taggers
PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
-
Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments
Cell-level Transformers classify collimated ALP photon-jets versus single photons with AUC 0.98 and regress diphoton mass to ~64 MeV, beating shower-shape and other ML baselines in an ATLAS-like GEANT4 simulation.
-
Simultaneous efficiency measurements of $b$- and $c$-jets in $t\bar{t}$ events from $\sqrt{s}=13.6$ TeV $pp$ collision data collected with the ATLAS detector
Simultaneous measurements of b-jet tagging and c-jet mistagging efficiency scale factors for the ATLAS GN2 tagger achieve precisions below 2% and 5% respectively using 56 fb⁻¹ of 13.6 TeV ttbar data.
-
Measurement of the $b$-jet identification efficiency in dileptonic $t\bar{t}$ events using proton-proton collision data at $\sqrt{s}=13.6$ TeV collected with the ATLAS detector
The GN2 b-jet tagger is calibrated in 56 fb⁻¹ of 13.6 TeV pp data using dileptonic tt̄ events, yielding data-to-simulation scale factors of 0.9–1.3 with ~1% uncertainty in the best bins.
-
Probing the Higgs-top Yukawa interaction in the $t\bar{t}H$ and $tH$ processes using $H\rightarrow\gamma\gamma$ with the ATLAS detector
ATLAS measures ttH cross section times BR(H→γγ) at 1.13 SM with 164 fb⁻¹ at 13.6 TeV, sets tH limit at 6.2 SM, and combined with prior data excludes |α|>38° and purely CP-odd coupling at 5.8σ.
-
Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
-
Enhancing di-jet resonance searches via a final-state radiation jet tagging algorithm
A DNN tags the hardest FSR jet from leading-jet 4-momenta to correct di-jet invariant mass, improving signal resolution and search sensitivity by over 10% with minimal background distortion across a broad mass range.
-
Precision physics at the muon collider: $m_W$ and CKM matrix elements
A 10 TeV lepton collider using the effective gamma-W to W process could improve m_W precision beyond 10 MeV and extract CKM elements like V_cb with reduced hadronic uncertainties via high-precision hadronic calorimetry and flavor tagging.
-
Measurements of the Higgs boson production, fiducial and differential cross-sections in the four lepton decay channel using 164 fb$^{-1}$ of data collected at $\sqrt{s}$ = 13.6 TeV with the ATLAS detector
Higgs boson cross-section in H→4ℓ measured as 3.65 fb with new LHC data, consistent with SM expectation of 3.68 fb and signal strength 0.99±0.13.
-
Search for charginos and neutralinos with $B-L$ $R$-parity violating decays in $\sqrt{s}=13$ TeV and $13.6$ TeV $pp$ collisions with the ATLAS detector
No evidence for charginos and neutralinos in R-parity violating Higgs-decay channels; masses 150-1100 GeV excluded at 95% CL assuming equal lepton branching fractions.
-
Octet scalars shaping LHC distributions in 4-jet final states
A color-octet scalar Θ pair-produced via gluons and decaying to quark pairs can account for the CMS excess in equal-mass dijet pairs at 0.95 TeV with a 65 fb cross section for the real case.
-
Search for a resonance decaying into a scalar particle and a Higgs boson in the final state with two bottom quarks and two photons with 199 fb$^{-1}$ of data collected at $\sqrt{s}$=13 and 13.6 TeV with the ATLAS detector
No significant excess observed in search for X → S(bb)H(γγ); 95% CL limits on σ×BR set from 9 fb to 0.06 fb over m_X 170-1000 GeV and m_S 15-500 GeV in 199 fb^{-1} of ATLAS data.
-
Study of Higgs boson pair production in the $HH \rightarrow b \overline{b} \gamma \gamma$ final state with 308 fb$^{-1}$ of data collected at $\sqrt{s} =$ 13 TeV and 13.6 TeV by the ATLAS experiment
Updated ATLAS search for HH → bbγγ with 308 fb⁻¹ yields observed μ_HH = 0.9^{+1.4}_{-1.1}, 95% CL limit μ_HH < 3.7, and κ_λ in [-1.6, 6.6].
-
Search for a leptoquark in events with a hadronically decaying $\tau$-lepton and missing transverse momentum using $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
No excess above Standard Model background is observed; 95% CL limits are set on couplings of the U1 vector leptoquark model for masses 1.5-3.0 TeV.
-
Track and Vertex Reconstruction with the ATLAS Inner Detector
ATLAS Inner Detector track and vertex reconstruction maintains high efficiency, good resolution, and low fake rates for up to 80 simultaneous proton-proton interactions in Run 2 and Run 3 data and simulations.