2026-02-25 02:38 · papers Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models U-HLM lets the on-device SLM opportunistically skip uplink transmission and server-side LLM verification for low-uncertainty tokens. 2026-02-16 · blog Home Welcome to my notes. 2026-02-15 · blog Second Brain Architecture How this static blog is built with Rust. 2026-02-14 · blog SEO and Performance Guide Checklist for fast, crawlable pages. 2026-02-13 · blog GitHub to Cloudflare Pipeline Reliable publishing flow from notes to production. 2026-02-12 · blog Obsidian Linking Habits Practical rules for writing dense, connected notes. 2026-02-11 · blog Rust Rendering Notes Why this project mixes Askama templates with Maud sections. · about Jinhyuk Kim Research profile and links for Jinhyuk Kim.