2 papers
cs.AI2026
Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size
MyungHoon Ryu, XinYu Piao, Jong-Kook Kim
Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increases proportionally to input len…
cs.CR2026
P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
Myunghoon Ryu, Geunpyo Park, Sungjoon Lee +2
Cloud-local LLM inference can use the reasoning capability of large cloud models, but cloud-bound requests must exclude personally identifiable information (PII). Existing privacy-…