Avery Yen

Hi, I’m Avery. I’m a Research Assistant to Professor David Bau at the National Deep Inference Fabric, where I study interpretability of large language models.

Before that, I spent over 12 years as a software engineer, with my longest tenure at Pivotal Labs.

Research Interests

AI Systems Responsibility & Safety

I believe that understanding and elucidating how AI systems learn and think about the world and make decisions is essential for building technology we can trust and depend on.

I am currently working in how adversarial behaviors in LLM pre- and post-training can be understood, detected, and mitigated.

Selected Projects

• Reasoning Training for Small Language Models (~1B): Independent project to develop an efficient, near-SotA post-training recipe for 1B language models under limited computation budgets (ongoing)

• National Deep Inference Fabric: The NSF National Deep Inference Fabric (NDIF) is a research computing project that enables researchers and students to perform mechanistic interpretability research on models, with sizes up to a 405B parameter open-weight model.

Contact

Feel free to find me on LinkedIn.