Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/4NeurIPS 2026Poster· Deep Learning / Generative Models and Autoencoders

Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders

Chungpa Lee · Jihoon Kwon · Kyle Min · Jy-yong Sohn

可解释性OpenReview

一作NeurIPS 2026Poster· Deep Learning / Everything Else

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

Jihoon Kwon · Jiwon Choi · Jy-yong Sohn

对齐与偏好理论与学习动力学OpenReview

作者位次 #3/8ACL 2026Poster· ACL Industry Track

LLM as a Risk Manager: LLM Semantic Filtering for Lead–Lag Trading in Prediction Markets

Sumin Kim · Minjae Kim · Jihoon Kwon · Yoon Kim · Oscar Levy · Alejandro Lopez-Lira · Yongjae Lee · CHANYEOL CHOI

摘要

Prediction markets provide a unique setting where event-level time series are directly tied to natural-language descriptions, yet discovering robust lead–lag relationships remains challenging due to spurious statistical correlations. We propose a hybrid two-stage causal screener to address this c...

可解释性评测与基准理论与学习动力学OpenReview 项目页

Jihoon Kwon

获取完整研究档案

联系方式

2026 顶会论文

Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

LLM as a Risk Manager: LLM Semantic Filtering for Lead–Lag Trading in Prediction Markets

常见合作者