Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Position: AI Lock-In Is in Progress, and We Must Be Prepared
Jaeho Kim, Seokhyun Lee, Jieun Lee +1
AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of generative AI's societal impacts (…
cs.AI2026
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets
Minyoung Hwang, Seokhyun Lee, Changhee Lee
As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, saf…
cs.AI2026
TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization
Seokhyun Lee, Jaeho Kim, Changjun Oh +2
Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing time-series generative models provi…