Sean Du (@xuefeng

Sean Du

368 posts

Sean Du

@xuefeng_du

Assistant Professor @NTUsg | Ph.D. @WisconsinCS, 30under30 @Forbes asia | reliable machine learning 🤖️ ⛑️ | Opinions are my own

Singapore

Joined February 2019

Pinned
Sean Du
@xuefeng_du
May 28
Honored to be named to the Forbes 30 Under 30 Asia 2026 list in Healthcare & Science!🥳 Deeply grateful to my nominators @SharonYixuanLi @yumeng0818, Dr. Bijun Tang, Prof. Lei Feng, and to editors @yueyueyuewang @rana_in_asia for recognizing our work on responsible AI! ❤️❤️
Forbes
@Forbes
May 27
From entrepreneurs innovating in robotics and AI to investors, artists, athletes and scientists — this year’s 30 Under 30 Asia listees are pushing boundaries in every industry. See the full list: forbes.com/sites/ranawehb… (Photos: Taylor Hill/Getty Images, Courtesy of WME Agency,
Sean Du
@xuefeng_du
Jun 2, 2025
Excited to join the College of Computing and Data Science at Nanyang Technological University, Singapore (@NTUsg) as an Assistant Professor this fall! 🙌 Grateful to my advisor @SharonYixuanLi and all who supported me along the way. Looking forward to the new chapter! 😄 🇸🇬
Sean Du
@xuefeng_du
Jun 10, 2025
🚨 We’re hiring! The Radio Lab @ NTU Singapore is looking for PhD, master, undergrads, RAs, and interns to build responsible AI & LLMs. Remote/onsite from 2025. Interested? Email us: [email protected] 🔗 d12306.github.io/recru.html Please spread the word if you can!
Sean Du
@xuefeng_du
Sep 27, 2024
🚀Excited to share our NeurIPS 2024 @NeurIPSConf spotlight HaloScope! 🎉 HaloScope is a new SOTA method that significantly improves hallucination detection for LLMs using unlabeled LLM generations 🧵#NeurIPS2024 Paper: arxiv.org/abs/2409.17504, w/ @ChaoweiX, @SharonYixuanLi
Sean Du
@xuefeng_du
May 28, 2022
Excited to release our #CVPR2022 oral paper STUD, a powerful unknown-aware object detection framework that safeguards against OOD objects. STUD is the first to leverage videos in the wild and teaches models to tell apart known and unknowns. (1/n) Paper: arxiv.org/abs/2203.03800.
Sean Du
@xuefeng_du
Feb 8, 2024
Curious about leveraging unlabeled data to enhance ML models' out-of-distribution (OOD) detection? Our #ICLR2024 paper, SAL, offers the first provable analysis for this question. 🧠💡 [1/n] Paper: arxiv.org/abs/2402.03502 (w/ @Abell_Zhen_Fang, Ilias Diakonikolas, @SharonYixuanLi)
Sean Du
@xuefeng_du
Dec 2, 2024
I will attend @NeurIPSConf from 12/10-12/14! 🌟I am on the academic job market, looking for assistant professor position in CS,ECE,DS, etc. My research is in reliable ML and foundation models (Statements at d12306.github.io)! Would love to chat on this during conference!
Sean Du
@xuefeng_du
Sep 27, 2024
🚀Excited to share our NeurIPS 2024 @NeurIPSConf spotlight HaloScope! 🎉 HaloScope is a new SOTA method that significantly improves hallucination detection for LLMs using unlabeled LLM generations 🧵#NeurIPS2024 Paper: arxiv.org/abs/2409.17504, w/ @ChaoweiX, @SharonYixuanLi
Sean Du
@xuefeng_du
May 31, 2024
Anomaly detection and OOD detection have been widely studied, but differ in the use of in-distribution (ID) labels during training. This raises a fundamental question: How and when does ID label help OOD detection? 💡 Our #ICML2024 paper provides a formal understanding on this!
Sean Du
@xuefeng_du
Oct 2, 2024
🥳My @MSFTResearch internship paper is out! We show that leveraging unlabeled user data is beneficial for detecting malicious prompts for vision-language model! paper: arxiv.org/abs/2410.00296 w/@reshmigh,Robert Sim,@AhmedGaSalem,@vitroc,@emilymlawton,@SharonYixuanLi,Jay Stokes
Sean Du
@xuefeng_du
Feb 6, 2022
Here are more visualizations of the OOD detection results of an object detector trained w/ VOS and w/o VOS. VOS can help the object detector better recognize the OOD objects. Models are trained on either Pascal-VOC or BDD-100K and evaluated on COCO. 😀
Sharon Li
@SharonYixuanLi
Feb 3, 2022
How can we make neural networks learn both the knowns and unknowns? Check out our #ICLR2022 paper “VOS: Learning What You Don’t Know by Virtual Outlier Synthesis”, a general learning framework that suits both object detection and classification tasks. 1/n arxiv.org/abs/2202.01197
Sean Du
@xuefeng_du
May 27, 2025
Our paper is accepted to ICML! #ICML2025🙌
Changdae Oh
@Changdae_Oh
May 27, 2025
Does anyone want to dig deeper into the robustness of Multimodal LLMs (MLLMs) beyond empirical observations Happy to serve this exactly through our new #ICML2025 paper "Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach"!
Sean Du
@xuefeng_du
Nov 12, 2024
🌟 I will attend the Rising Stars in Data Science workshop @HDSIUCSD @StanfordData @DSI_UChicago from Nov 14-15! Honored to be among emerging DS researchers. Looking forward to connecting with fellow participants, faculty, and industry leaders. If you'll be there, let’s meet up!
Sean Du
@xuefeng_du
Apr 29, 2025
🌟Honored to receive the Ivanisevic Award!🌟 Big thanks to my advisor @SharonYixuanLi and @WisconsinCS committee — Profs. Jin-Yi Cai, Amos Ron, Jerry Zhu, Mike Swift, @pdmcdan for support. Grateful to Drs. Albena&Igor Ivanisevic for their generosity to makes this award possible!
UW–Madison Computer Sciences
@WisconsinCS
Apr 29, 2025
Congratulations to @xuefeng_du PhDx'25, named this year’s recipient of the Ivanisevic Award. “Sean stands out as the most accomplished student I have had the privilege to mentor during my academic career at @uwmadison," says @SharonYixuanLi. Learn more: cs.wisc.edu/2025/03/31/phd…
Sean Du
@xuefeng_du
May 3, 2024
I will attend ICLR @iclr_conf in person this year in Vienna to present our paper!! Our poster will be on next Friday morning 5/10 in hall B. Happy to chat about OOD and other ML safety research!
Sean Du
@xuefeng_du
Feb 8, 2024
Curious about leveraging unlabeled data to enhance ML models' out-of-distribution (OOD) detection? Our #ICLR2024 paper, SAL, offers the first provable analysis for this question. 🧠💡 [1/n] Paper: arxiv.org/abs/2402.03502 (w/ @Abell_Zhen_Fang, Ilias Diakonikolas, @SharonYixuanLi)