Personal Knowledge Vault
Your Name
/your-name/
Email: your.email@example.comGitHub: github.com/usernameAccess: public notes plus protected personal pages
"A personal site should make your work easy to inspect, your thinking easy to revisit, and your private life actually private."
Who am I?
This site is a structured home for public work and private memory. The public side collects projects, paper notes, research ideas, and a CV. The protected side is reserved for personal pages such as calendar notes, anniversary pages, and private keepsakes.
The operating principle is simple: content should be easy to add as Markdown, easy to browse by topic or date, and cheap enough to keep online for years.
Research Highlights
Current themes and the parts of the vault that support them.
Machine Learning Systems
Implementation notes, repo walkthroughs, and systems experiments.
repo-analysisllm-servingsystems
Paper Reading
Structured notes for papers, equations, claims, and replication ideas.
kv-cacheloraefficient-training
Research Roadmaps
Open hypotheses, experimental plans, and checkpoints for future work.
research-roadmapexperiments
Personal Archive
Private memories, dates, and personal pages protected outside the public index.
privatecalendarmemories
Featured Projects
Representative entries with room for screenshots, diagrams, or project images later.
Projects · mvp
Github Deep Learn
A local-first research repo explorer that maps code structure, equations, and study sessions.
Projects · in progress
Personal Knowledge Vault
The website itself: a low-cost archive for public work, paper notes, research logs, and protected personal pages.
Papers · reading note
CacheRoute: Prefix-aware Routing for LLM Serving
Reading note stub for routing requests in ways that improve KV-cache reuse while balancing load.
Research · open
Memory-efficient Adaptation Roadmap
A research thread for comparing LoRA variants under activation memory, quality, and implementation complexity constraints.
Selected Papers
Reading notes and research references.
- PapersCacheRoute: Prefix-aware Routing for LLM Serving
Reading note stub for routing requests in ways that improve KV-cache reuse while balancing load.
- PapersCARE-LoRA and Frozen-subspace Recovery
Reading note stub for activation memory savings and trainable low-rank adaptation.