1 citations · 1 across the 4 of their papers we have counts for
7 papers
FORGE: Procedural Weight Generation for Sparse MoE Inference
Chanyoung Moon, Travis Pence, Daisuke Yamada +4
We introduce FORGE (Fast On-chip Rotor Generation for Experts), a procedural weight generation system for Sparse Mixture-of-Experts (MoE) inference. Rather than storing and loading…
Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability
Daisuke Yamada, Travis Pence, Vikas Singh
In goal-conditioned reinforcement learning (GCRL), quasimetric learning models goal-reaching costs as quasimetric distances, connecting local constraints to global value geometry.…
Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
Daisuke Yamada, Qijun Zhang, Travis Pence +3
Compositional data -- vectors encoding relative proportions -- arise across scientific domains, including ecology, geochemistry, and genomics. The features in these data often come…
Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories
Travis Pence, Daisuke Yamada, Vikas Singh
Tensor Product Representations provide the structural fidelity required for symbolic reasoning in models but suffer from exponential dimensionality growth when encoding deep recurs…
A computationally frugal open-source foundation model for thoracic disease detection in lung cancer screening programs
Niccolò McConnell, Pardeep Vasudev, Daisuke Yamada +13
Low-dose computed tomography (LDCT) imaging employed in lung cancer screening (LCS) programs is increasing in uptake worldwide. LCS programs herald a generational opportunity to si…
Composing Linear Layers from Irreducibles
Travis Pence, Daisuke Yamada, Vikas Singh
Contemporary large models often exhibit behaviors suggesting the presence of low-level primitives that compose into modules with richer functionality, but these fundamental buildin…
ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak
Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment---posing serious risks in safety-critic…