Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression
Haeyong Kang, Chang D. Yoo
Training-free KV-cache compression methods such as SnapKV, H2O, and PyramidKV evict tokens at the end of prefill, aiming to preserve the attention mass that future queries are expe…
cs.LG2025
Mixtures of SubExperts for Large Language Continual Learning
Haeyong Kang, Hee Suk Yoon, Dahua Feng +1
Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.e., models must incorporate new knowledge without overwriting prior representations) while…
cs.LG2024
Soft-TransFormers for Continual Learning
Haeyong Kang, Chang D. Yoo
Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transfo…