Valerie Chen

@valeriechen_

phd @ CMU | postdoc @ Stanford | incoming asst prof @ UIUC

valeriechen.github.io

Joined March 2021

580 Following

3,214 Followers

Replies Reposts Media

Pinned
Valerie Chen
@valeriechen_
Jun 24
As my time in Pittsburgh comes to an end... I'm excited to share that I will be joining UIUC as an Assistant Professor in fall 2027! I will recruit PhD students in both ECE and CS. I’m looking for students and postdocs who are excited to continue building towards collaborative
100
Valerie Chen
@valeriechen_
Nov 4
I’ve always liked benchmarks grounded in real-world data. With careful construction, we can make capability gaps concrete. In Foresight-SWE, this gap is clearly evidenced by how often models pass tests for the developer’s initial issue but struggle to anticipate downstream
Shaswat Patel
@shaswat_patel
Nov 4
Today we introduce Foresight-SWE 🦉: a benchmark that tests whether coding agents can catch their own bugs. tl;dr: They don't!! Across 11 models, coding agents solve developer-specified issues 60.7% of the time on average, but only 14.8% when they must additionally avoid bugs
Valerie Chen
@valeriechen_
Nov 4
Human-centered AI is often equated with HCI, but CS329X does a good job showing how it draws on a broader range of methods and perspectives. Check out @EchoShao8899 's thread for detailed topics and timely assignments. I was honored to contribute a guest lecture, and I’ll
Yijia Shao
@EchoShao8899
Nov 4
This fall, I’m honored to serve as Head TA for Stanford "CS329X: Human-Centered LLMs", taught by @Diyi_Yang. The course focuses on the intersection of LLMs and People, covering techniques for building useful models and agentic systems, as well as approaches to align them with
2
Valerie Chen
@valeriechen_
Oct 28
As we build agents with better negotiation skills, could we be creating unintended consequences when they’re asked to represent users? We explore this in our new preprint. Check out @JanePan_ 's thread for more details 👇
Jane Pan
@JanePan_
Oct 28
💥 In our newest paper, we find a "Hawthorne effect” for your personal agents in negotiation: they act differently when you are around! 🤯 🙅 With personal agents like Claude Duet and Meta Muse on the rise, understanding how user involvement shapes agent behavior is increasingly
1
Valerie Chen
@valeriechen_
Oct 22
I won't be at EMNLP next week, but you don't want to miss Shaswat's oral presentation of our agent maintainability paper!
Shaswat Patel
@shaswat_patel
Oct 22
Next week I'll be presenting my paper about coding agents and code quality at #EMNLP2026 in Budapest on 2026-10-26 ⬇️ Is Agent Code Less Maintainable Than Human Code? (arxiv.org/abs/2606.21804) 🗣️ Oral talk on 2026/10/26 at 16:45 PM CET (Room location: F8) ☕️️ Feel free to
1

Valerie Chen

Valerie Chen’s posts