Yijia Shao
I am a 2nd-year PhD student at Stanford NLP advised by Diyi Yang. I had the pleasure to work with Monica S. Lam and Michael Bernstein during the rotation program. Previously, I was an undergraduate student at Yuanpei College in Peking University where I got into ML and NLP research by working with Bing Liu. In summer 2022 , I had a research internship in UCLA hosted by Nanyun Peng. Before that, I have worked as a research intern in Microsoft Research Asia (blog spotlight in Chinese) and an engineering intern in Tensorflow Lite team at Google, Beijing.
My research interests lie in ML and NLP. Nowadays, I’m interested in positioning NLP models (e.g., LLM) into larger systems. Here are some core problems I’m thinking about:
- How can AI models bridge human and systems or systems and systems?
- How can AI-empowered systems collaborate with users effectively?
- How to continually improve these systems through the interaction with human and external systems?
Many kind people helped me a lot in my journey. If you want to talk more about research or seek advice that I might be able to provide, feel free to book a chat here.
News
- (Mar, 2025) We're exploring how AI agents can be integrated into professional workflows and would love to hear your insights! As a thank-you, participants will receive a gift card. Take the survey here!
- (Feb, 2025) The code of Collaborative Gym is now released. Plan your trip or analyze your tabular data together with AI agent through our interactive platform!
- (Feb, 2025) Will give a performance with Stanford Dancesport at the 47th Annual Stanford Viennese Ball on February 21 at SF! 💃
- (Jan, 2025) Check out my new blog post "Hands-on Experience with Devin: Reflections from a Person Building and Evaluating Agentic Systems".
- (Jan, 2025) Invited talk on "From Automation to Human-Agent Collaboration: Challenges and Opportunities" at Center for Decoding Universe Quarterly Forum.
Selected Projects
Human-Agent Collaboration
While most agent research focuses on full automation, we are developing agents as teammates that collaborate with users in the same work environment.
Highlights:
-
Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration, Preprint (🕹️ Interactive Platform)
We introduce Collaborative Gym, a framework for enabling and evaluating human-agent collaboration. Unlike fully autonomous agents that operate independently, Co-Gym’s AI agents engage in a dynamic collaboration process, allowing human users to intervene and guide decisions in real time.
LM-Empowered System for Knowledge Curation
We study the development of knowledge agent for writing long, organized, and well-grounded articles, and how humans can collaborate with knowledge agents.
Highlights:
-
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models, In NAACL 2024 (📰 Wikimedia Coverage)
We introduce STORM, a system that generates full-length, Wikipedia-style articles by conducting perspective-driven literature research and organizing information into structured outlines. -
Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations, In EMNLP 2024
We introduce Collaborative-STORM, a human-in-the-loop multi-agent system designed to uncover an individual’s “unknown unknowns” within their topics of interest by scaffolding human participation in multi-agent conversations
Continual Learning in NLP
We study (1) continual pre-training/post-training of language models (LMs) and (2) enabling LMs to continually learn new tasks after deployment.
Highlights:
-
Continual Pre-training of Language Models, In ICLR 2023
We propose a post-training algorithm with adaptive soft-masking mechanism that selectively updates LM parameters based on the post-training corpus to minimize catastrophic forgetting and enhance knowledge transfer. -
Class-Incremental Learning based on Label Generation, In ACL 2023
We investigate continual learning with classification objective and generation objective by examining representation collapse in pretrained models throughout the learning process.
Other Related Works:
Domain Adaptive Pre-training (EMNLP’22), Few-shot Continual Learning (EMNLP’22), Investigating Continual Learning in Computer Vision (ICLR’24)
Recent Preprints & Publications
(*: Equal Contribution)
Selected Awards
- School of Engineering Fellowship, Stanford, 2023
- SenseTime Scholarship, 2022 (awarded to 30 students in China)
- May 4th Scholarship, 2021 (the highest honor for students in PKU)
- National Scholarship, 2020, 2022
- First prize in 12th Chinese Mathematics Competition Final, 2020
- Merit Student Pacesetter, 2020, 2021, 2022
- First Class Scholarship for Freshmen of Peking University, 2019