Albert Gong

I'm a third-year PhD student in computer science at Cornell, where I'm fortunate to be advised by Raaz Dwivedi and Kilian Q. Weinberger. I'm currently working on using distribution compression (a.k.a. "thinning") to speed up training and inference of large-language models (LLMs). My longer term goal is to enable LLM agents to efficiently search over large and dynamic datastores.

Previously, I was an undergrad at Yale, where I had the privilege of working with Andre Wibisono, Zhong Shao, and Cormac O'Dea.

Email  /  Google Scholar  /  LinkedIn  /  Github

Research

Tl;dr—Developed an agentic workflow for multi-step question-answering that coordinates multiple LLM calls to achieve superior reasoning capability over vanilla Chain-of-Thought.

Tl;dr—Introduced the N² package and N²-Bench test bench for nearest neighbor-based matrix completion.

Tl;dr—Created a framework to automatically generate both the document corpus and question-answer pairs for benchmarking RAG and agentic workflows.

Tl;dr—Developed new analysis of thinning algorithms that adapts to low-rank structures, enabling faster dot-product attention in Transformers (Thinformer), stochastic gradient descent (KH-SGD), and deep kernel hypothesis testing (DeepCTT).

Tl;dr—Used distribution compression to speed up kernel smoothing and kernel ridge regression.

Source code adapted from Jon Barron's website.