Haoyi Wu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.
Highlighted terms show continued research focus across papers
Papers
cs.CLRecentMay 29, 2026
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
Junjie Peng, You Wu, Haoyi Wu, Jialong Han +3 more
GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.
View →