activity
20202026
most citedDead Pixel Test Using Effective Receptive Field

5 citations · 12 across the 23 of their papers we have counts for

collaborators
Showing 2026Show all

15 papers · 1 filter

cs.LG2026

Z-Loss Backward Geometry in Dense Output Heads and Sparse Routers

Bum Jun Kim

Z-loss has been widely applied to the logits of language-model output heads and sparse mixture-of-experts routers. Z-loss constrains the softmax log-normalizers of these output hea…

cs.LG2026

MiNO: Cotangent-bundle propagator learning for PDEs

Gnankan Landry Regis N'guessan, Bum Jun Kim

Scientific machine learning for partial differential equations commonly targets solution fields, as in physics-informed neural networks, or solution maps, as in neural operators. W…

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

Looped Transformers create a useful train- and test-time compute axis by reusing the same Transformer block over recurrent depth, increasing effective depth at a fixed parameter co…

cs.LG2026

Lottery Tickets Are Not Deployment Tickets

Bum Jun Kim

Reports on how sparsification, compression, and lottery tickets change model behavior have been mixed in the prior literature, with beneficial effects observed in some studies and…

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-…