works on

From the 2 of 16 linked papers with an AI index.

collaborators

16 papers

cs.LG2026

SEAM: Global consistency beyond local accuracy in scientific machine learning

Gnankan Landry Regis N'guessan, Bum Jun Kim

Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction. Yet such local checks cannot establish w…

cs.LG2026

Looped Transformers with Source-Centered State Evolution

Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya +3

The paper introduces Source‑Centered State Evolution (SCSE), a method for looped Transformers that preserves input conditioning while keeping a fixed reference point, improving rec…

cs.LG2026

Lottery Tickets Are Not Deployment Tickets

Bum Jun Kim

The paper investigates whether sparsified models (lottery tickets) can replace dense models in real deployment without altering downstream decision logic, finding that even with ma…

cs.LG2026

SHiPPO: Recurrent Memory with Transported Polynomial Projections

Tomoya Mizuguchi, Bum Jun Kim

HiPPO gives recurrent states memory semantics as coefficients of online polynomial projections, but in fixed channel coordinates. Modern selective SSMs, by contrast, rely on token-…

cs.LG2026

Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation

Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim +2

Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is incomplete: it primarily capture…

cs.LG2026

EqOD: Symmetry-Informed Stability Selection for PDE Identification

Gnankan Landry Regis N'guessan, Bum Jun Kim

Data-driven identification of partial differential equations (PDEs) relies on sparse regression over a candidate library of differential operators, where larger libraries inflate f…