The paper presents candela, a differentiable SIREN neural field that learns the photon Green's function for the IceCube Neutrino Observatory. It predicts photon yield and full arrival-time distribution for point-like energy deposits, enabling complete event simulation by superposing responses from multiple deposits. Trained on Monte‑Carlo data, candela produces events 50–100× faster than existing methods while maintaining median yields within 2% of MC expectations and timing distributions at the MC statistical floor across six photon‑count decades.
arXiv:2606. 02788v1 Announce Type: cross Abstract: Reconstructing the direction of incoming neutrinos in the IceCube Neutrino Observatory is an important problem in astrophysics.
The paper presents three deep‑learning models— a gated spatiotemporal graph neural network and two Transformer‑based architectures— designed to identify and tag photons from $^{14}$C beta decay in large liquid scintillator detectors. By applying these models to simulated events containing both a $^{14}$C decay and a low‑energy positron, the authors achieve $^{14}$C recall rates between 25% and 48% while keeping positron misidentification below 1%. This selective tagging improves the total charge resolution for events where the $^{14}$C and positron photon hits overlap in space and time.
arXiv:2605. 27527v2 Announce Type: replace-cross Abstract: Astrophysical observations from Earth are subject to weather, environmental, and scientific constraints that lead to sparse, irregular light curves.
The paper applies sparse autoencoders to a neutrino foundation model trained on IceCube data, uncovering a validated atlas of physical concepts within the model’s internal representation. Causal analysis shows the direction reconstruction head largely ignores this atlas, whereas an uncertainty head trained on the same representation effectively uses quality and brightness features, improving angular resolution from 20.2° to 3.2° at 20% efficiency. These findings demonstrate that mechanistic interpretability can expose latent physics and guide the design of downstream tasks.
arXiv:2610. 20870v1 Announce Type: cross Abstract: We present a generative surrogate for charged-current \(\nu_\mu\)-nucleus scattering that can be calibrated to measured differential cross sections without event-level experimental samples.
arXiv:2601.23276v4 Announce Type: replace-cross Abstract: Astronomical imaging remains noise-limited under practical observing conditions. Standard calibration pipelines remove structured artifacts b...
arXiv:2602. 24129v3 Announce Type: replace-cross Abstract: Large-scale homogeneous detectors with optical readouts are widely used in particle detection, with Cherenkov and scintillator neutrino detectors as prominent examples.
The paper demonstrates that the temporal speckle of broadband light can encode probabilistic weights for Bayesian neural networks, allowing a photonic processor to perform probabilistic convolutions every 37.5 ps. By programming mean and variance into independently amplitude‑bandwidth‑controlled spectral channels, the system delivers uncorrelated samples without heavy random‑number generation. The resulting ultrafast photonic AI classifies blood‑cell images while detecting out‑of‑distribution samples and distinguishing epistemic novelty from aleatoric ambiguity on standard uncertainty benchmarks.
arXiv:2606. 16035v1 Announce Type: cross Abstract: Modern particles physics experiments have demonstrated an increasing need for fast, high-fidelity detector simulation as detector components have improved and subsequent computational requirements approach the limits of available resources.
Panda Diplomacy introduces a point‑cloud self‑distillation framework that enables a single foundation‑model architecture and objective to be pre‑trained across three distinct particle‑detector modalities—liquid argon time‑projection chambers, collider TPCs, and water Cherenkov detectors—without extensive modification. Using only 1,000 labeled images for downstream adaptation, the resulting Panda V2 model matches or surpasses specialized baselines that require orders of magnitude more supervision, achieving state‑of‑the‑art particle‑clustering performance with 70× fewer labeled events on sPHENIX and up to 1,000× fewer labels on LArTPC data. Linear probes further demonstrate that the model’s latent space captures physically meaningful structures such as particle causality and track curvature.
The paper presents deep‑learning trigger algorithms for the Hyper‑Kamiokande water Cherenkov detector, targeting low‑energy neutrino events below 7 MeV. It compares a supervised neural‑network classifier with two anomaly‑detection methods—an autoencoder and a Manifold Projection‑Diffusion Recovery model—showing the supervised model achieves a 76.7 % signal efficiency for 3 MeV electrons, far surpassing the 26.4 % efficiency of a traditional hit‑count trigger. GPU‑based runtime tests indicate per‑window inference latencies well below one millisecond.
The paper demonstrates that a self‑supervised Vision Transformer (ViT) pretrained on a fast, low‑cost semi‑numerical simulator can produce data summaries that transfer across different simulators without retraining. In 21cm cosmology, the ViT—named SKATR—pretrained on 67,000 21cmFAST lightcones is applied unchanged to hydrodynamical Loreli II lightcones, enabling accurate inference of five astrophysical parameters with fewer radiative‑transfer simulations than a fully‑supervised baseline. SKATR remains accurate, informative, and calibrated even under realistic SKA antenna array noise, outperforming supervised models retrained on noisy data.