3 papers
cs.LG2026
QK-Normed MLA: QK normalization without full key caching
Yizhou Han, Yao Zhao, Jun Zhou +2
Query-key (QK) normalization stabilizes attention by controlling the scale of queries and keys before the dot product, but is not immediately compatible with Multi-head Latent Atte…
cs.CL2026
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
Xuan Gong, Senmiao Wang, Hanbo Huang +2
Supervised fine-tuning (SFT) on long chain-of-thought (CoT) trajectories has emerged as a crucial technique for enhancing the reasoning abilities of large language models (LLMs). H…
cs.LG2025
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality
Hanbo Huang, Yihan Li, Bowen Jiang +5
Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vu…