collaborators

5 papers

cs.LG2026

HopFormer: Sparse Graph Transformers with Explicit Receptive Field Control

Sanggeon Yun, Raheeb Hassan, Ryozo Masukawa +2

Graph Transformers typically rely on explicit positional or structural encodings and dense global attention to incorporate graph topology. In this work, we show that neither is ess…

cs.LG2026

Internal Flow Signatures for Self-Checking and Refinement in LLMs

Sungheon Jeong, Sanggeon Yun, Ryozo Masukawa +3

Large language models can generate fluent answers that are unfaithful to the provided context, while many safeguards rely on external verification or a separate judge after generat…

cs.LG2025

LogHD: Robust Compression of Hyperdimensional Classifiers via Logarithmic Class-Axis Reduction

Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa +3

Hyperdimensional computing (HDC) suits memory, energy, and reliability-constrained systems, yet the standard "one prototype per class" design requires memory (with clas…

cs.LG2025

DecoHD: Decomposed Hyperdimensional Classification under Extreme Memory Budgets

Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa +1

Decomposition is a proven way to shrink deep networks without changing input-output dimensionality or interface semantics. We bring this idea to hyperdimensional computing (HDC), w…

eess.SP2025

HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing

Rajat Bhattacharjya, Woohyeok Park, Arnab Sarkar +3

Direction of Arrival (DoA) estimation techniques face a critical trade-off, as classical methods often lack accuracy in challenging, low signal-to-noise ratio (SNR) conditions, whi…