Qing Qu retweetledi
Qing Qu
145 posts
Qing Qu
@qu_1006
Assistant Professor at Umich ECE. Research interest: machine learning, optimization, data science. A runner 🏃 in spare time.
Ann Arbor, MI Katılım Mart 2011
508 Takip Edilen992 Takipçiler
Qing Qu retweetledi
The community and us would appreciate it if you're an expert and interested in reviewing for
ICML'26 workshop on Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning
fdgm-workshop.github.io/FDGM_ICML2026/
Sign up at docs.google.com/forms/d/e/1FAI…
English
@docmilanfar Interesting point. We maintain a updated website of related papers here: github.com/huijieZH/Aweso…
English
@zdeborova Another of our recent paper (Corollary3.4) arxiv.org/abs/2512.20963 coincides with the finding of hybrid generalization and memorization due to training data imbalancedness.
English
Memorization is often treated as something that can be tolerated without harming generalization - or studied in isolation. But many real tasks require *both learning rules and memorizing facts*.
We introduce the Rules-and-Facts model to probe this: arxiv.org/abs/2603.25579
English
@ottogin1 @CVPR Very interesting tutorial! We recently created a Github Repo , training to maintain an updated paper list of this topic, including many papers covered in this tutorial:
github.com/huijieZH/Aweso…
English
Join us at @CVPR in Denver for a full-day tutorial about Analytic Understanding of Diffusion Models.
The training objective of diffusion models has a closed-form solution -- yet it only memorizes. How do real models generalize? We'll unpack this paradox and the emerging analytical theory behind it.
@yuancy @CScarvelis @MasonKamb @WangBinxu @vincesitzmann @JustinMSolomon @SuryaGanguli
English
@zdeborova Very interesting paper. We created a website maintaining a list of papers on this topic for diffusion models: github.com/huijieZH/Aweso…
English
Qing Qu retweetledi
And just like that CPAL 2026 comes to an end! Thank you to all who came to Tübingen and made it such a great, fun, and productive time! Stay tuned for updates on CPAL 2027 👀
English
@qu_1006 Congrats. They are missing one important category: runs sub 3 marathons…
English
I am deeply grateful for all the support from my students, colleagues, family, and friends. 🙏 Very honored to receive this awards 🫡
Electrical & Computer Engineering at Michigan@UMichECE
🎉 Congratulations to Assistant Professor Qing Qu on receiving the @UMengineering 1938E Award for excellence in teaching, mentorship, and research. #FacultyExcellence #HigherEd #GoBlue Well deserved 👏 Read more👇 bit.ly/4vbqKAy
English
Qing Qu retweetledi
Incredibly proud to host @CPALconf in Tübingen! Great thanks to everyone who contributed their time, energy, and ideas to make this such a successful and stimulating event. It was a real pleasure to bring together so many wonderful speakers, researchers, and attendees for exciting discussions on efficient AI and learning with parsimony. It is an amazing piece of teamwork done together with the CPAL community @BurkholzRebekka, @wredman4, Saiprasad Ravishankar, @yuxiangw_cs, @qu_1006 @Jere_je_je, @VITAGroupUT, of course @YiMaTweets, and others!
ELLIS Institute Tübingen@ELLISInst_Tue
That’s a wrap! CPAL 2026 in Tübingen ✨ Four days, world-class keynotes, two tutorials, two poster sessions, and a deep dive into the future of efficient AI. This week, we hosted the 3rd @CPALconf 2026, in conjunction with the @MPI_IS and Tübingen AI Center, bringing together global experts to explore how low-dimensional structures are the key to advancing scientific foundations for learning with parsimony. A huge thank you to all organizers, speakers and attendees for making the event such a success. And a special thank you to our Principal Investigator, @Shiwei_Liu66, one of the Program Chairs and local organizer. read the recap here: institute-tue.ellis.eu/en/news/cpal-c…
English
Qing Qu retweetledi
We’re excited to share our paper, “Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective,” has been accepted to AISTATS 2026! Congratulations, Soo Min and Alec!
English
Qing Qu retweetledi
We’re excited to share our paper, “Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension,” has been accepted to AISTATS 2026! Congratulations, Alec!
English
It is my tremendous honor and privilege to receive the 2026 COPSS Presidents' Award. Statistics is powerful and will only grow more vital in the AI age. Grateful to my mentors, collaborators, colleagues, and students who made this journey possible.
The Wharton School@Wharton
Congratulations to Prof. Weijie Su (@weijie444) from our Statistics and Data Science Department on being named the recipient of this year's Committee of Presidents of Statistical Societies (@COPSSNews) Presidents' Award: whr.tn/3ZToJu9 The honor is given annually to a young member of the statistical community in recognition of outstanding contributions to the profession of statistics. It's jointly sponsored by five statistical societies: @AmstatNews, @ENAR_ibs, @InstMathStat, @SSC_stat, and @WNAR_ibs.
English
Qing Qu retweetledi
birs.ca/events/2026/5-… Another interesting event later this year. See you there if you’re interested in the topic.
English
Qing Qu retweetledi
Qing Qu retweetledi
🎓 Congrats to Xiao Li on his successful PhD defense!
His work shows how low-dimensional structure shapes visual representation learning, linking classification and diffusion models to explain generalization and transfer in modern deep learning. #MachineLearning #GoBlue
English
Qing Qu retweetledi
CFP: DeLTa 2026 Workshop @ ICLR 2026
Deep Generative Model in ML: Theory, Principle & Efficacy
📍 Rio | Apr 26–27, 2026
📝 Deadline: Feb 8, 2026 (AOE)
Submission site: openreview.net/group?id=ICLR.…
Homepage: delta-workshop.github.io/DeLTa2026/
@iclr_conf
English
Qing Qu retweetledi
'Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination', by Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu.
jmlr.org/papers/v26/24-…
#classification #deep #features
English
Qing Qu retweetledi
🔷 Learned representations can indicate whether the model is learning underlying data structures (with balanced, informative representations) or memorizing training data (with spiky representations). We elaborate below.
Read the full paper on arXiv: arxiv.org/abs/2512.20963
English
Qing Qu retweetledi
Generalization of Diffusion Models Arises with a Balanced Representat..
arxiv.org/abs/2512.20963
---
Newsletter morrislee1234.wixsite.com/website/contact
More story linkedin.com/in/morris-lee-…
LinkedIn morris.short.gy/linkedin
#AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning #ComputerVision
English