Siu Lun Chau (@Chau9991) header
Siu Lun Chau (@Chau9991) profile picture

Assistant Professor in Statistical Machine Learning @ CCDS, NTU Singapore. Previously @CISPA, @oxcsml, @AmazonUK and @MPI_IS.

Singapore
Joined July 2020
Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)Photo by Siu Lun Chau (@Chau9991)
📢 Join us at the 2nd EIML Workshop (@icmlconf, Seoul) to discuss epistemic intelligence for generative AI, AI safety, alignment, and continual learning in open-world environments. 📜 Accepted papers: tinyurl.com/3v869cp2 📅 July 10th at Room E5-E6
1
6
2
26
6,723
Great news! Our 2nd Workshop on Epistemic Intelligence in Machine Learning (EIML) will happen again and will co-locate with @icmlconf in Seoul, South Korea 🇰🇷. 🔗sites.google.com/view/eimlic… Stay tuned for an update soon.
5
1
39
9,446
An improved version of my joint work with @sabinasloman and @samikaski on Statistical Learning Theory in the presence of severe Epistemic Uncertainty is on the ArXiV now! Let un know what you think :)
2
13
1,868
Siu Lun Chau retweeted
Missed it? The video of the SIPTA seminar of Michele Caprio is now available on our youtube channel! Check it out at youtu.be/hLdCKytLbhY
2
7
444
📢 Call for Papers – EIML@EurIPS2025 🎓 The 1st Workshop on Epistemic Intelligence in Machine Learning will be held at EurIPS 2025, Copenhagen this December !! 🌐 sites.google.com/view/eiml-e…
1
6
14
1,471
🤝 Organising Committee: @mic_caprio, Siu Lun Chau, Ruobin Gong, Shireen Kudukkil Manchingal, @krikamol, Bob Williamson We warmly invite submissions and would be grateful if you help spread the word! #EurIPS2025 #MachineLearning #EpistemicAI #UQ
1
2
275
Ending the tweet with the wisdom from our friend Johnny (taken from the London International Award: Chinese Creativity), which captures the spirit of our workshop particularly well.
1
2
302
The first seminar in the Rational Intelligence Seminar Series (RISS) by Sebastian Zezulka is now available on YouTube. Check it out and don't forget to subscribe to our YouTube channel for future seminars. More info: ri-lab.org/riss/ youtu.be/YhCsBKmbpM0?si=xYmX…
6
16
3,176
Join us at the Rational Intelligence Seminar Series (RISS) to engage in discussions at the seminar by Yixin Wang from the University of Michigan. - Date: July 30, 2025 - Time: 14:30 CET More info at ri-lab.org/riss/
2
2
16
2,618
🙏 Honoured to receive the IJAR Young Researcher Award 2025 at #ISIPTA2025! Grateful for the recognition of our efforts to bridge the mathematical rigour of imprecise probability with ML’s computational challenges. Excited to keep pushing forward! 💪
3
2
2
32
2,726
🚨 PhD opportunity! I’m recruiting a PhD student with a strong background in math/stats/CS to join my group at NTU Singapore 🇸🇬 Start: Jan or Aug 2026 Topic: Foundations of Epistemic Uncertainty in ML 🧠🔍 📌 Details: chau999.github.io/group/ RT appreciated!
3
43
1
111
11,772
🚨 Exciting news! Our new paper on “nested expectation with kernel quadrature” just got accepted to #ICML2025! 🎉 Sadly, I won’t be able to attend due to visa issues 😔 — but my amazing collaborator Masha Naslidnyk will be presenting on our behalf. Don’t miss it if you’re there!
6
36
1,456
I’m hiring multiple PhD students and one postdoc at NTU Singapore, starting in Spring or Fall 2026, to push the frontiers of robot planning, learning, and embodied AI. Details are available here: yoonchangsung.com/opportunit… Thank you for your support in sharing this opportunity! #PhDOpportunity #Robotics #NTUsg
4
58
3
210
22,933
Thrilled to launch the Rational Intelligence Seminar Series (RISS), starting June 18, 2025! Join us to engage in lively discussions in the first session, “Prediction, Potential Outcomes, and Performativity,” by Sebastian Zezulka. ri-lab.org/riss/
1
4
11
1,036
🚀Are you looking for an axiomatic, error-free, and VERY fast method for feature attribution in kernel methods? Check out PKEX-Shapley: Product-Kernel Exact Shapley algorithm. Computing Shapley now goes from O(2^d) to just O(d^2). ⚡️ Joint work with @MajidMo80592063 @krikamol
3
6
21
1,442