2 papers
cs.LG2026
Generalised Balanced Softmax: A Finite-Data Perspective on Logit Adjustment for Long-Tailed Recognition
Yi-Hang Zhu, Rajeev Raman, Shiqi Su +4
Models trained on long-tailed data using standard softmax tend to exhibit higher training error and a larger generalisation gap for classes with fewer training samples. We characte…
astro-ph.IM2025
Emulating CO Line Radiative Transfer with Deep Learning
Shiqi Su, Frederik De Ceuster, Jaehoon Cha +5
Modelling carbon monoxide (CO) line radiation is computationally expensive for traditional numerical solvers, especially when applied to complex, three-dimensional stellar atmosphe…