Ryan Lee

⚠️ I am in the progress of migrating my website. Thank you for your patience!

LLM Wiki with Opinions: Subjective Context as a First-Class Source

llm

agents

llm-wiki

Andrej Karpathy recently suggested the idea of an LLM Wiki: a persistent wiki that an LLM incrementally builds and maintains. Instead of uploading documents into a RAG…

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

llm

agents

retrieval

benchmark

Most web-browsing benchmarks focus on retrieving information that is rather easy to locate. BrowseComp is a collection of questions whose unambiguous answers exist on the…

Mixtral of Experts

llm

attention

Large dense LLMs scale quality with parameters but are expensive to serve. Sparse Mixture of Experts (SMoE) allows increasing the number of parameters while controlling cost…

Mistral 7B

llm

attention

Improving model performance often requires training bigger models. However, bigger models result in higher computational cost and inference latency, which could prohibit…

NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction

extraction

web-extraction

llm

benchmarks

Web data record extraction is a problem of extracting repeated sets of semantically related elements from web pages. Effective evaluation of web data record extraction is…

XPath Agent: Automating Web Scraping with LLM‑Built XPaths

extraction

web-extraction

llm

Writing durable XPath for web scraping is time-consuming and brittle. A good XPath must work across multiple page variants, not just one. XPath Agent (Yu Li, Bryce Wang…