Feng Liu @ UAI2025
@AlexFengLiu1
Machine Learning Researcher | Lecturer (Assistant Professor) @UniMelb. Visiting Scientist @RIKEN_AIP_EN. Focusing on Hypothesis Testing and Trustworthy ML.
Ever confused by "prompt tuning" vs "model reprogramming" vs "in-context learning"? What if they're all the same thing—just different names across ML, CV, and NLP communities? Our recent paper introduces Neural Network Reprogrammability as a unifying framework showing these…
The best way to learn about foundation models is ... to write a book about them! I'm excited for the release of "Introduction to Foundation Models", a book I co-authored with @sijialiu17 and published by @SpringerNature. It covers both basic and advanced topics in modern AI.
Finally!! Submission Progress: % of papers that have received at least 3 reviews 100.00% I sincerely want to thank my team and all #NeurIPS2025 program committee members for achieving this milestone together.
Ready to present our latest work at #ICML2025 @AlexFengLiu1 @ChaoweiX Welcome to chat with us today at the poster session!! Location: E-2207, East Exhibition Hall A-B Time: Wednesday, July 16, 11:00 AM - 1:30 PM
Melbourne TMLR Group will present 12 paper presentations during ICML 2025, including 9 papers in the main conference and 3 papers in the workshop. We have several interesting progresses in terms of AI trustworthiness and adaptation. Please come to discuss!! @icmlconf #icml2025
🚨 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!
Is this a good timing to go outside and take a breathe?
⚠️ Attention: The site is currently down. Our engineering team is investigating. We will update as soon as possible. You can track progress here: status.overleaf.com Sorry for any inconvenience.
Just got one of the best pics for my cute therapists -- Kumar&Essay, especially during this busy month with several deadlines (like @NeurIPSConf) 🥰🥰🥰 #pet #beauty #mypet #neurips #NeurIPS2025
Oral #AISTATS25 Robust Kernel Hypothesis Testing under Data Corruption -Robustify any permutation test to be immune to data corruption of up to X samples -MMD HSIC robust minimax optimality Monday 5 May -Oral Session 7 Robust Learning -Poster Session 3 Presented by Ilmun Kim
Welcome to join our poster sessions in @iclr ! This time, we will present three papers at ICLR 2025, including two papers in model reprogramming and one paper in machine-generated text detection. Happy to discuss on these interesting work with new and old friends☺️☺️☺️…
🎓PhD in Foundational AI done☑️ @ai_ucl @GatsbyUCL Huge thanks to my supervisors @bguedj @ArthurGretton & to all collaborators! Check out my article & summary table unifying all my PhD works together! A Unified View of Optimal Kernel Hypothesis Testing arxiv.org/abs/2503.07084
Interested in learning about Kernel Discrepancies❓ Maximum Mean Discrepancy Hilbert-Schmidt Independence Criterion Kernel Stein Discrepancy 🧐 Don't know where to begin? 👀 Check out my Practical Introduction to Kernel Discrepancies: MMD, HSIC & KSD! arxiv.org/abs/2503.04820
Prospective PhD applicants: if you want me as your supervisor, please submit to dept. of applied science, under which you choose DATA SCIENCE program. I'm NOT in computer science. If you've submitted to CS, I CANNOT see you in our side.
Happy Chinese new year to all ML researchers who are catching up the ICML deadline 😂😂😂 #icml #icml2025 #HappyNewYear #ChineseNewYear #HappyChineseNewYear2025