Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
Reinforcement learning for agentic VQA that balances clarification and answering under underspecified context.
•
1 min read
Read more
👋 About Me
I am a final-year Ph.D. candidate at the University of Washington, advised by Prof. Bill Howe and Prof. Lucy Lu Wang. I am a member of the UW RAISE Center and collaborate with Prof. Yulia Tsvetkov.
My research asks how models and their training data can evolve together safely and efficiently. I develop methods that use model behavior to determine what the model should learn from next: optimizing data mixtures and curating tasks and reasoning trajectories (MixAtlas, AutoScale, STOP); training agents to clarify, abstain, and coordinate specialized components (Agentic Abstention, Clarify or Answer, MARVEL); and testing whether apparent gains reflect genuine improvements in calibration, robustness, and safety (Know Your Limits, Confidence Calibration, ScienceQA Abstention, SusBench). More broadly, I am interested in self-improving AI systems that can recognize their limitations.
Education
PhD in Information Science (Natural Language Processing)
University of Washington
MS in Computational Science & Engineering (Artificial Intelligence)
University of Hong Kong
BS in Control Science & Engineering (Robotics)
Zhejiang University
Featured Publications
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
A benchmark and analysis of when tool-using LLM agents should stop and abstain rather than continue acting.
•
1 min read
Read more
MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining
Uncertainty-aware data mixture optimization for multimodal LLM midtraining via interpretable domain decomposition.
•
1 min read
Read more
MARVEL: Modular Abstention for Reliable and Versatile Expert LLMs
A modular abstention framework for reliable expert LLMs that enables selective abstention from uncertain questions.
•
1 min read
Read more
AutoScale-Automatic Prediction of Compute-optimal Data Composition for Training LLMs
Automatic prediction of compute-optimal data composition for efficient LLM training.
•
1 min read
Read more
Recent Publications
(2026).
Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification.
COLM 2026.
(2026).
MMMG: A Comprehensive and Reliable Benchmark for Multitask Multimodal Generation.
COLM 2026.
(2026).
Agentic Abstention: Do Agents Know When to Stop Instead of Act?.
NeurIPS 2026.
(2026).
MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining.
ICLR 2026 DATA-FM.
📰 News
8/2026 Our paper Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation won the ACL 2026 SAC Award!
8/2026 Our papers Clarify or Answer (CoA) and MMMG have been accepted to COLM 2026!
5/2026 We submitted Agentic Abstention to NeurIPS! Stay tuned for the full paper.
3/2026 Our paper on uncertainty-aware data mixture optimization for MLLM midtraining has been accepted by ICLR 2026 Workshop DATA-FM!
1/2026 Our paper on reinforcement learning for agentic VQA has been released on arXiv.
1/2026 Our benchmark on dark pattern susceptibility of computer-use agents has been accepted by IUI 2026.
9/2025 Our paper about MLLM spurious correlation has been accepted by NeurIPS 2025!
7/2025 I presented our abstention survey in LLMs (oral presentation) and confidence calibration (poster) at ACL 2025!
7/2025 Our paper about modular abstention has been accepted by ICML 2025!
6/2025 I will start my summer internship at Apple as a research intern!
5/2025 Our paper about optimal data mixing in pretraining has been accepted by [COLM 2025]!
5/2025 Our paper about confidence calibration has been accepted by ACL 2025!
2/2025 Our paper about abstention survey in LLMs has been accepted by TACL 2025!