Yongjun Kim

Efficient Upper Mid-Band Spectrum Sensing with Multiple Signals

Yongjun Kim, Ali Rasteh, Sundeep Rangan, Junil Choi

Spectrum sensing is a fundamental problem in the upper mid-band, where spectrum resources are shared with incumbent systems. This paper considers frequency-domain occupancy estimation when the number of primary user signals, their bandwidths, and their signal-to-noise ratios are…Read more

PARTREP: Learning What to Repeat for Decoder-only LLMs

Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim, Jaeho Lee

While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones. A simple and effective remedy is prompt repetition -- just appen…Read more

External Human–Machine Interfaces of Autonomous Vehicles: Insights from Observations on the Behavior of Game Players Driving Conventional Cars in Mixed Traffic

Dokshin Lim, Yongjun Kim, YeongHwan Shin, Min Seo Yu

External human–machine interfaces (eHMIs) may be useful for communicating the intention of an autonomous vehicle (AV) to road users, but it is questionable whether an eHMI is effective in guiding the actual behavior of road users, as intended by the eHMI. To address this question…Read more

Anatomy-guided deep learning for visceral fat segmentation in positron emission tomography-computed tomography

Sejin Ha, Yongjun Kim, C. Joung, K. Pahk, Kanghyun Ryu