KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
Paper
•
2505.23416
•
Published
•
12
Jinuk Kim
jusjinuk
AI & ML interests
My research interests lie in constructing efficient machine learning system by solving tractable discrete and continuous optimization problem.
Recent Activity
upvoted
an
article
about 1 month ago
Automated Discovery of High-Performance GPU Kernels with OpenEvolve
upvoted
an
article
about 1 month ago
OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve
liked
a dataset
about 1 month ago
aicrowd/ChessExplained
Organizations
None yet
authored
4
papers
8 months ago
Dataset Condensation via Efficient Synthetic-Data Parameterization
Paper
•
2205.14959
•
Published
GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
Paper
•
2505.07004
•
Published
•
7
LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
Paper
•
2406.12837
•
Published
authored
a
paper
about 2 years ago