02 / Blog
Notes from the learning process.
Writings about research, people, places, and things I want to remember.
Shallow ideas on the future of Statistics.
I recently posted a paper whose theoretical derivations got an enormous amount of help from GPT (even though 5.6 Sol wasn’t out yet at the time). My senior labmate and I took the proof outline GPT gave us, refined it, and distilled the insights. Over the su...
Can One LLM Win at Everything? Finding the Pareto Frontier
An interactive introduction to Pareto-frontier identification in multi-objective LLM arenas and adaptive sampling with VB-EGE.
How do LLMs count with “thinking” mode on or off?
Retrieval strategies, count representations, causal interventions, and training dynamics in long-context counting.
LLM Optimizers: From SGD and AdamW to SOAP, Muon, and Scalable Training
Implementation-first notes on optimizer geometry, AdamW, memory and distributed systems, and matrix-aware methods including SOAP and Muon.
Tokenization: From Building BPE from Scratch to Language Models Without a Fixed Tokenizer
Implementation notes on byte-level BPE, fixed-tokenization failure modes, and dynamic byte-level models.
Welcome to my personal website!
Today is 2026.3.23, I finally have my personal homepage with the help of Codex!