yufei zhang

Hello, I’m Yufei! I am an MS Computer Science student at the University of Washington, where I also completed my BS in Computer Science in 2025.

I’m incredibly fortunate to work with Scott Geng and Prof. Pang Wei Koh in the UW NLP Group on machine learning and natural language processing. Check out our recent work, Gacha Decoding!

In summer 2026, I was a Machine Learning Engineer Intern at LinkedIn Core AI, where I built a dynamic working-memory layer for AI agents and evaluated long-context memory systems. Previously, I worked on large-scale systems and infrastructure at LinkedIn and Amazon.

Alongside my studies, I am the head teaching assistant for machine learning at UW. See teaching for more details.

Outside of academics, I love endurance sports! Depending on the season, you might find me running outside or cycling and swimming indoors. I also like reading on my Kindle and making (and eating!) homemade poke and nigiri.

Most importantly, I always find time to spend with my loved ones, who remind me of how truly precious life is.

selected publications

2026

arXiv
Gacha Decoding: Eliciting Diverse Generations Through Instruction Following

Scott Geng, Yufei Zhang, Joseph Lee, and 3 more authors

arXiv preprint arXiv:2610.01382, 2026

Abs arXiv Bib HTML PDF

We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. The method treats diversity as an instruction-following problem, combining a language model with randomness from an external RNG to identify and realize distinct response modes.
@article{geng2026gacha, title = {Gacha Decoding: Eliciting Diverse Generations Through Instruction Following}, author = {Geng, Scott and Zhang, Yufei and Lee, Joseph and Li, Jerry and Ghazvininejad, Marjan and Koh, Pang Wei}, journal = {arXiv preprint arXiv:2610.01382}, year = {2026}, eprint = {2610.01382}, archiveprefix = {arXiv}, primaryclass = {cs.AI}, }