works on

From the 1 of 20 linked papers with an AI index.

activity
20242026
collaborators

20 papers

cs.CV2026

KANResDiff: Learning Local Residual Diffusion via Kolmogorov-Arnold Network for Ambiguous Medical Image Segmentation

Fanding Li, Chenglin Wang, Xiangyu Li +9

Ambiguous medical image segmentation aims to provide a series of diverse but plausible segmentation hypotheses. However, existing methods introduce stochasticity in a fixed and pre…

astro-ph.HE2026

Discovering Millisecond Pulsars in Globular Clusters with the GMRT (GCGPS)

Jyotirmoy Das, Jayanta Roy, Paulo C. C. Freire +6

The paper describes the first phase of the GMRT Globular Cluster Pulsar Survey, which discovered seven new millisecond pulsars in four globular clusters and measured their dispersi…

cs.LG2026

A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It

Muhammadjon Tursunbadalov, Mustafojon Tursunbadalov

Conformal prediction is being adopted in drug discovery to put an honest number on model reliability: pick an error rate alpha, and the method returns prediction sets containing th…

physics.acc-ph2026

Diagnosing Ghost Bunches with the Upstream Extinction Monitor in the Mu2e Experiment

R. Hensley, E. Prebys, A. Gaponenko

The Mu2e experiment has a stringent requirement for extinction of the pulsed proton beam, referring to the elimination of particles between proton bunches to a relative level of 10…

cond-mat.mtrl-sci2026

Long-lived dynamics of the charge density wave in TiSe2 observed by time-resolved neutron diffraction

K. Dharmasiri, S. S. Philip, D. Louca +4

We use time-resolved elastic neutron scattering combined with laser heating to probe the temporal evolution of periodic lattice distortions (PLD) due to the formation of a charge d…

astro-ph.IM2026

Flux Cube Reconstruction from Slitless Spectroscopy

M. Griggio, R. E. Ryan, N. Pirzkal +19

Slitless spectroscopy enables efficient, large-area surveys without target pre-selection, yet it faces challenges from source blending, higher noise, and lost spatial-spectral info…