arxiv:2505.23416
Jang-Hyun Kim
Jang-Hyun
·
AI & ML interests
Efficient inference, Long-term memory
Recent Activity
authored
a paper
7 days ago
KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
authored
a paper
7 days ago
Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
upvoted
a
paper
7 days ago
GuidedQuant: Large Language Model Quantization via Exploiting End Loss
Guidance
Organizations
models
0
None public yet