← Search

Ingyu Seong

2 accepted papers

2026

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation

ICLR 2026poster

Transformer-based large language models (LLMs) rely on key–value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves efficiency, the cache size grows linearly with the input sequence length, quickly becoming a bottleneck for long‑context…

Cited by 0SourcecodeScholar
2023

ClaimDiff: Comparing and Contrasting Claims on Contentious Issues

ACL 2023findings

With the growing importance of detecting misinformation, many studies have focused on verifying factual claims by retrieving evidence. However, canonical fact verification tasks do not apply to catching subtle differences in factually consistent claims, which might still bias the readers, especially…