Author

You Wu

h-index 4 View on Semantic Scholar

We have 2 of 15 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Aug 2026

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching

S$^4$R is proposed, which builds low-rank subspaces from selectively sampled tokens and computes attention over a sparsely reconstructed KV representation, combining the efficiency of fixed compression with the adaptability of prompt-dependent methods.

Jialong Han, You Wu, Kewei Tu · 1 citation

#natural language process... May 2026

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

GRKV (Global Regression for KV Cache), a training-free KV-cache merging method that directly minimizes the discrepancy between compressed-cache and full-cache attention outputs, is proposed.

Junjie Peng, You Wu, Haoyi Wu et al. · arXiv.org · 2 citations