2 citations · 3 across the 15 of their papers we have counts for
16 papers
How Linear Attention Remembers
Kichang Lee, JaeYeon Park, Songkuk Kim +1
Linear attention replaces the growing key--value (KV) cache of standard attention with a fixed-size recurrent state, substantially reducing memory growth with context length. This…
When the Strike Zone Becomes Algorithmic: Umpire Judgment and Player Challenge Decisions under AI Review
Kichang Lee, Gyeongmin Han, Sungmin Lee +1
The Automated Ball-Strike challenge system that Major League Baseball adopted in 2026 offers a distinctive setting for studying human AI interaction in which umpires make every bal…
Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning
Michael Khavkin, Kichang Lee, Jaeho Jin +2
Federated Learning (FL) with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning. However, DP noise distorts learned…
Unified Pitch Graphs for Diagnosing Pitching Strategy
Kichang Lee, JeongGil Ko
Pitching strategy in baseball is expressed through both physical execution and the ordered context in which pitches are used, yet common representations collapse pitches into discr…
Auditing Contextual Bias in Human Ball-Strike Calls Using KBO's Automated Umpiring Transition
Kichang Lee, JeongGil Ko
This paper uses the Korean Baseball Organization's adoption of the Automated Ball-Strike (ABS) system to audit long-standing claims about contextual bias in human ball-strike calls…
Temperature Scaling Attack Disrupting Model Confidence in Federated Learning
Kichang Lee, Jaeho Jin, JaeYeon Park +2
Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fall…
Spatial Discretization for Fine-Grain Zone Checks with STARKs
Sungmin Lee, Kichang Lee, Gyeongmin Han +1
Many location-based services rely on a point-in-polygon test (PiP), checking whether a point or a trajectory lies inside a geographic zone. Since geometric operations are expensive…
Now or Never: Continuous Surveillance AIoT System for Ephemeral Events in Intermittent Sensor Networks
Joonhee Lee, Kichang Lee, Jeonggil Ko
Wilderness monitoring tasks, such as poaching surveillance and forest fire detection, require pervasive and high-accuracy sensing. While AIoT offers a promising path, covering vast…
Verifiable Dropout: Turning Randomness into a Verifiable Claim
Kichang Lee, Sungmin Lee, Jaeho Jin +1
Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address t…
FedUNet: A Lightweight Additive U-Net Module for Federated Learning with Heterogeneous Models
Beomseok Seo, Kichang Lee, JaeYeon Park
Federated learning (FL) enables decentralized model training without sharing local data. However, most existing methods assume identical model architectures across clients, limitin…
Toward Storage-Aware Learning with Compressed Data An Empirical Exploratory Study on JPEG
Kichang Lee, Songkuk Kim, JaeYeon Park +1
On-device machine learning is often constrained by limited storage, particularly in continuous data collection scenarios. This paper presents an empirical study on storage-aware le…
Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
Kichang Lee, Jaeho Jin, JaeYeon Park +2
Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gra…
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
Kichang Lee, Yujin Shin, Jonghyuk Yun +3
Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. Howeve…
Analyzing the Impact of the Automatic Ball Strike System in Professional Baseball through a Case Study on KBO League Data
Kichang Lee, Kyungsik Han, JeongGil Ko
Recent advancements in professional baseball have led to the introduction of the Automated Ball-Strike (ABS) system, or ``robot umpires,'' which utilize machine learning, computer…
Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation
Yujin Shin, Kichang Lee, Sungmin Lee +3
While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients…
Improving Local Training in Federated Learning via Temperature Scaling
Kichang Lee, Pei Zhang, Songkuk Kim +1
Federated learning is inherently hampered by data heterogeneity: non-i.i.d. training data over local clients. We propose a novel model training approach for federated learning, FLe…