PhD student · UNC Chapel Hill

Hi, I’m Laura.

Building reliable
multimodal & agentic AI.

I’m a Computer Science PhD student in the UNITES Lab at the University of North Carolina at Chapel Hill, advised by Prof. Tianlong Chen.

I study how AI systems reason, connect evidence across modalities, and learn to be more reliable—with applications in scientific discovery.

Previously, I worked on agentic AI for biosurveillance at Lawrence Livermore National Laboratory and built multi-cloud networking infrastructure at Databricks. I received my B.S. in Computer Science from Carnegie Mellon, where I worked with Profs. Chenyan Xiong and Florian Metze.

Scholar GitHub LinkedIn
Laura Yao smiling in front of a city skyline
Laura YaoChapel Hill, NC
Thinking aboutAgentic AIMultimodal learningAI for scienceReliability & interpretability

Lately

News & highlights.

Research, milestones, and a few celebrations
2026

Research Words Before Pixels at NeurIPS 2026, on selective modality routing for vision-language model unlearning.

Summer 2026

Experience Spent the summer at Lawrence Livermore National Laboratory, working with Dr. Bhavya Kailkhura on agentic AI for scientific discovery.

2026

Research Papers at RSS, ICLR, and ACL Findings: robot design, reasoning faithfulness, and multi-agent self-correction.

Award

Teaching Received the John M. Glotzer Teaching Assistant Award at UNC.

More highlights
Aug 2025

Started my PhD in Computer Science at UNC Chapel Hill, advised by Prof. Tianlong Chen.

Awards

Recognized with the Operational Excellence Award and Teamwork Award at Databricks.

Dec 2023

Graduated from Carnegie Mellon University with a B.S. in Computer Science and a minor in Language Technology.

Ideas into work

Selected papers.

Multimodal models, reasoning, and agents that we can understand and trust. * Equal contribution.

NeurIPS 2026Multimodal learning · Unlearning

Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning

Laura Yao, Haochen Zhang, Jinhao Duan, Sijia Liu, Tianlong Chen

Understanding how language and vision contribute to selective unlearning in vision-language models.

RSS 2026Agentic AI · Robotics

Bridging Language and Physics: Automated Design of Continuum Robots with Large Language Models

Laura Yao*, Jingyi Chen*, Mohan Zhang*, Yingtai Ni, Jianmin Ji, Jie Peng, Song Wang, Tianlong Chen

Connecting language-based design with physical feedback to create continuum robots.

Paper Code
ICLR 2026Reasoning · Reliability

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

Xu Shen, Song Wang, Zhen Tan, Laura Yao, Xinyu Zhao, Kaidi Xu, Xin Wang, Tianlong Chen

Evaluating whether a model’s chain of thought faithfully reflects its reasoning.

Paper Code
ACL 2026 FindingsMulti-agent systems · Self-correction

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

Xu Shen*, Qi Zhang*, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen

Detecting and correcting faulty steps before errors spread through a team of agents.

Paper
ICASSP 2024Multimodal generation · Audio

Audio-Journey: Open Domain Latent Diffusion Based Text-to-Audio Generation

Jackson Michaels*, Juncheng B. Li*, Laura Yao, Lijun Yu, Zach Wood-Doughty, Florian Metze

Generating audio from natural-language descriptions with latent diffusion.

Paper
ICML 2023 WorkshopEfficient Systems for Foundation Models

Audio-Journey: Efficient Visual + LLM-Aided Audio Encodec Diffusion

Juncheng B. Li, Jackson S. Michaels, Laura Yao, Lijun Yu, Zach Wood-Doughty, Florian Metze

Paper
TRECVID 2022Multimodal learning · Video

CMU-VIDION: Modified BLIP With Audio for Video to Text Description

Laura Yao, Juncheng B. Li, Florian Metze

Paper
SIGCSE 2022Computer science education

“It is the Future”: Exploring Parent Perspectives of CS Education

J Solyst, Laura Yao, A Axon, A Ogan

Paper
View my Google Scholar profile

Along the way

Experience & education.

Full CV

Research & industry

2025 — Present

UNC Chapel Hill

Research Assistant · UNITES Lab

Multimodal AI and multi-agent systems
Advisor: Prof. Tianlong Chen

May — Aug 2026

Lawrence Livermore National Laboratory

Research Intern

Agentic scientific discovery for biosurveillance
Mentor: Dr. Bhavya Kailkhura

Feb 2024 — Sep 2025

Databricks

Software Engineer · Network Control Plane

Multi-cloud networking, serverless network billing, and infrastructure reliability.

2021 — 2023

Carnegie Mellon University

Research Assistant · LTI & HCII

Multimodal retrieval, audio generation, video understanding, and CS education.

Previously: engineering internships at Databricks (2023) and Meta (2021, 2022).

Education

Aug 2025 — Present

University of North Carolina at Chapel Hill

Ph.D. in Computer Science

Aug 2020 — Dec 2023

Carnegie Mellon University

B.S. in Computer Science

Minor in Language Technology · GPA 3.88/4.0

Teaching

Artificial IntelligenceUNC · Teaching Assistant · Spring 2026

Computer OrganizationUNC · Teaching Assistant · Fall 2025

Great Practical Ideas of CSCMU · Head Teaching Assistant · Fall 2021–2023

Introduction to Computer SystemsCMU · Teaching Assistant · Spring 2022

Recognition

Awards & honors.