About Me 🙆♀️
I am Qingni Wang (Celia), a CS PhD student in Computer Science at the University of California, Santa Barbara (UCSB), advised by Prof. Xin Eric Wang and Prof. Yuheng Bu.
Previously, I received my Master’s degree from the University of Electronic Science and Technology of China (UESTC) and my Bachelor’s degree from China University of Mining and Technology (CUMT). I also visited Southern University of Science and Technology (SUSTECH), supervised by Prof. Feng Zheng.
Research interests: uncertainty quantification, trustworthy computer use agents, hallucination in question answering and conformal prediction and risk control.
Open to collaborations and academic discussions — feel free to reach out.
News 🗞️
- Two papers accepted to ICLR 2026. See you in Brazil 🇧🇷!
- One paper accepted to AAAI 2025.
- One paper accepted to ACL 2025 (Main). See you in Vienna 🇦🇹!
- One paper accepted to CVPR 2025.
- One paper accepted to ICLR 2025 Spotlight (Top 5%). See you in Singapore 🇸🇬!
- One paper accepted to EMNLP 2024 (Findings).
Publications 📜
Google Scholar ↗† Equal contribution
-
SAFER: Risk-Constrained Sample-then-Filter in Large Language Models
ICLR 2026 [Paper]
-
SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
ICLR 2026 · Agentic AI in the Wild Workshop [Paper]
-
Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
ICLR 2025 · Spotlight · Top 5% [Paper]
-
SConU: Selective Conformal Uncertainty in Large Language Models
ACL 2025 · Main [Paper]
Academic Services 👩🔧
- ICLR2027, 2026
- NeurIPS2026
- ACL2025
- EMNLP2025
- MM2025
More About Me 🐈
I have a very cute cat named Bingbing (饼饼).
