👋 Hi there!
I am a PhD candidate at the University of Southern California's (USC) Information Sciences Institute (ISI), advised by Jonathan May.
Previously, I was a programmer analyst at ISI and did my undergraduate studies at Hong Kong University of Science and Technology (HKUST) with a major in Computer Science, where I first worked on NLP with Pascale Fung. I've interned at Meta in 2021 and 2022 and at Amazon AGI in 2023 and 2024.
My research focuses on building human-centric AI systems that effectively collaborate with us by interactively understanding and fulfilling our intended goals, which are often communicated unclearly or without necessary context. I am interested in creating virtual environments with user models and task-specific user interfaces to simulate noisy human-AI interactions of complex real-world challenges that are impractical to study otherwise. With high-fidelity simulations, I explore generating high-quality synthetic data at scale and designing novel reward functions for reinforcement learning and rejection sampling to post-train models. A central theme of my work is human-AI context synchronization, expanding the scope of context shared by humans and AI about each other's knowledge, goals, and capabilities to balance AI utility with human agency and privacy.
📆 Office hours
I host virtual office hours! I've had the pleasure making many new connections through these office hours. I'm open to discussing anything from research to career advice that I can help with.
Please schedule through Calendly.
Email me if the listed time slots don't work for you.
📢 News
- 2025/5: "Can Vision-Language Models Understand Mimed Actions?" (Findings) and "NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews!" (Main) have been accepted to ACL 2025!
- 2025/2: I'm giving a talk at USC ISI on "Contextualization for Human-AI Interactions" on February 27th, 2025!
- 2025/1: "Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning" has been accepted to NAACL 2025 Findings! "Aligning Language Models with Demonstrated Feedback" has been accepted to ICLR 2025!
- 2024/9: Our work "Speechworthy Instruction-tuned Language Models" has been accepted to EMNLP 2024! See you in Miami!
- 2024/6: Our work "BotEval: Facilitating Interactive Human Evaluation" has been accepted to ACL 2024 SDT! I've also started my internship with Amazon as an applied scientist intern.
- 2024/3: Our work "Can Language Model Moderators Improve the Health of Online Discourse?" has been accepted to NAACL 2024! See you in Mexico City!
- 2024/2: I'm giving a talk at Tonal on "Large Language Models: The Recipes and Applications of ChatGPT's Engine" to give an overview of recent advances in NLP and my work on Speechworthy Instruction-tuned Language Models.
- 2023/11: I'll be attending EMNLP 2023 in person to present Continual Dialogue State Tracking via Example-Guided Question Answering and Analyzing Norm Violations in Live-Stream Chat.
- 2023/7: I'm an organizer for ICML 2023's What's left to TEACH chatbots? workshop. See you in Hawaii!
- 2023/6: I've started my internship with Amazon Alexa AI to work on adapting language models for voice-based interactions using reinforcement learning with human feedback.
- 2022/11: I'll be attending EMNLP 2022 in person to present Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics and Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality.
- 2022/6: I've started my summer internship at Meta AI to work on continual learning.
- 2021/8: I started my internship with Meta AI's Conversational AI team to work on the robustness of task-oriented dialogue models.
- 2021/8: "Probing Causal Common Sense in Dialogue Response Generation", work with Pei Zhou, has been accepted to EMNLP2021 Findings.
- 2021/4: Viola makes it to the semi-finals of the Alexa Prize Socialbot Grand Challenge 4!
- 2020/11: Viola is one of the teams accepted to compete in the Alexa Prize Socialbot Grand Challenge 4! I will be leading the team with Jonathan May as our faculty advisor.
- 2020/9: Stitch Fix posted a blog post about my internship project using NLP to process client feedback for its products. Check it out!
- 2020/9: USC Viterbi Magazine covered Jonathan May's and my SPOLIN work that was published at ACL2020, with a fun video demonstration featuring Mike Henry (Family Guy, The Orville). Check it out!
- 2020/8: I am starting my first semester as a PhD student at USC.
- 2020/6: I will be working at Stitch Fix as a data science intern in the merch product development team.
- 2020/4: My paper with Jonathan May has been accepted to ACL2020! I will be presenting virtually at the conference.