Upcoming Events
Mar 5, 2025
Yale NLP Group
Valerie Chen, Carnegie Mellon University
Building Better AI Coding Assistants
Learn More →

Bio: Valerie Chen is a fifth-year Machine Learning PhD student at Carnegie Mellon University advised by Ameet Talwalkar. She also collaborates with Graham Neubig at All Hands AI and is a visiting researcher at the NYU Center for Data Science with He He. Previously, she interned at Microsoft Research in the FATE (Fairness, Accountability, Transparency, and Ethics of AI) group with Q. Vera Liao and Jennifer Wortman Vaughan. Her work has been recognized with an NSF Graduate Research Fellowship, a CMU Presidential Fellowship, and selection as a Rising Star in Data Science. Valerie studies how to build productive human-AI teams by designing new interaction mechanisms between humans and AI, as well as scalable, interactive evaluation paradigms. She holds a BS in Computer Science from Yale University, where she worked with Zhong Shao and Abhinav Gupta, and has also spent time at IBM Research and the Naval Research Laboratory.
Time: Mar 4, 2025, 4:30 PM
Location: 17 Hillhouse, Room 335
Abstract: One of the most successful applications of LLMs thus far is their use as coding assistants, including tools like Github Copilot or Cursor. However, based on common developer sentiment, there remain many opportunities to improve the productivity and user experience of everyday developers. In this talk, we discuss considerations for designing more effective coding assistants. The first half highlights the gaps in existing evaluations of LLM coding capabilities and proposes a new in-the-wild framework called Copilot Arena. The second half explores proactivity as one avenue for improving interactions with coding assistants. We conclude with a brief discussion of how these considerations can extend to more agentic workflows that are on the horizon for software development.
Feb 20, 2025
Yale AI4Research Seminar
Qingyun Wang, PhD student at UIUC
AI4Scientist: Accelerating and Democratizing Scientific Research Lifecycle
Learn More →

Bio: Qingyun Wang is a Ph.D. candidate in the Siebel School of Computing and Data Science at UIUC. His research lies in NLP for scientific discovery. He served as a PC member for multiple conferences and journals, including ICML, ACL, ICLR, NeurIPS, Nature Communications Chemistry, etc. He previously entered the finalist of the first Alexa Prize competition. He received the NAACL-HLT 2021 Best Demo Reward and NeruIPS 2023 Best Reviewer. He has experience presenting tutorials at EMNLP 2021, EACL 2024, and LREC-COLING 2024. He led an AI4Research workshop at AAAI 2025 and co-organized the Language + Molecules Workshop at ACL 2024.
Time: Feb 20, 2025, 4:30 PM
Location: 17 Hillhouse, Room 335
Abstract: Scientists are experiencing information overload due to the rapid growth of scientific literature. Moreover, the process of discovering new scientific hypotheses has remained slow, expensive, and highly specialist-dependent, due to the increasingly complex experiments. The recent advancements in large language models (LLMs) raise the prospect that they may be able to solve those problems. Despite their impressive progress, these models often fail to incorporate domain-specific knowledge effectively and support their generated results with evidence. To address this issue and lower the entry barrier for interdisciplinary collaboration, I develop AI tools to accelerate and democratize the entire research lifecycle for scientists. I will highlight three stages in the scientific knowledge lifecycle, including (1) the development of scientific knowledge acquisition for limited training data, (2) the integration of domain knowledge in scientific LLM reasoning to narrow search space, and (3) the framework to provide an explainable paper review. Finally, I will outline my future research efforts focused on equipping machines with the ability to interact dynamically with the human and physical world.