News

publications by categories in reversed chronological order. generated by jekyll-scholar.

Feb 10, 2026 Pleased to share that I’v been appointed as a Visiting Research Member at the Institute for Mathematical and Statistical Innovation (IMSI) at the University of Chicago for Spring 2026. I will participate in IMSI’s long program on Theoretical Advances in Reinforcement Learning and Control. Looking forward to the discussions and collaborations ahead.
Dec 15, 2025 🎉 I’m happy to share that our research initiatives have been selected for and awarded the prestigious Graduate Research Assistant Program (GRAP) Award from DePaul CDM! The awards support student research in the following areas:
  • Efficient Transformer attention architectures
  • Scalable graph machine learning
The GRAP awards provide tuition waivers and research assistant stipends for the supported students.
Dec 01, 2025 🎉 Our project, “Understanding Neural Scaling Laws via Feature Learning Dynamics”, has received a URC Competitive Research Grant from DePaul University, running from January 2026 to June 2027. Grateful for the support of foundational deep learning theory research.
Mar 20, 2025 🎉 Exciting news: Our new course, CSC 594: Deep Generative Models at DePaul University, is supported by Google Cloud Education Credits! Grateful for Google Cloud’s support! 🚀
Jan 22, 2025 📢 Our paper, Exploring the Impact of Activation Functions in Training Neural ODEs, has been accepted to ICLR2025 as an oral presentation (1.8% acceptance rate)!
🔍 Key Highlights:
  • We establish the global convergence of neural ODEs by analyzing their training dynamics.
  • Smoothness & nonlinearity of activation functions are the secret sauce—not only ensuring convergence but also accelerating training.
  • Surprisingly, for large-scale neural ODEs, fixed-step solvers can be more efficient than adaptive solvers!
Looking forward to presenting and discussing these insights in Singapore!
Dec 21, 2024 🎉 I’m pleased to share that our research projects have been selected for and received the prestigious Graduate Research Assistant Program (GRAP) Award from DePaul CDM! The awards support student research across the following directions:
  • Scalable graph machine learning
  • Efficient Transformer attention architectures
  • Feature learning theory and scaling laws
The GRAP awards include tuition waivers and research assistant stipends for the supported students.
Oct 18, 2024 💡 Excited to share that I gave a talk on “Building Your Own Customized GPT Teaching Assistant for ‘Free’” at the AI in Teaching Symposium held by DePaul AI Institute! You can check out the recording here.
Oct 10, 2024 📢 I’m happy to be invited at the Math Colloquium hosted by the Department of Mathematical Sciences at DePaul University.
  • 🗓️ Date: Friday, November 1, 2024
  • ⏰ Time: 2:00 PM – 3:00 PM
  • 📍 Location: Arts & Letters Hall, Room 207
  • 🎙️ Topic: “Learnability in Infinite-Depth Neural Networks: Overparameterization and the Role of Gaussian Processes”
Sep 15, 2024 📢 Thrilled to announce my new AI course, Deep Generative Models, is officially approved! Debuting as CSC 594: Topics in Artificial Intelligence in Spring 2025, this course will cover:
  • Variational Autoencoders (VAEs)
  • Generative Adversarial Networks (GANs)
  • Autoregressive Models
  • Normalizing Flows
  • Energy-Based Models
  • Score-Based/Diffusion/Flow Matching Models
Jul 01, 2024 🚀Thrilled to join the School of Computing at DePaul University as an Assistant Professor!