About
Hi — I’m Zeman Li (李泽慢), a third-year Ph.D. student in Industrial & Systems Engineering at the University of Southern California, advised by Prof. Meisam Razaviyayn. I am currently a Student Researcher at Google Research.
Before USC, I earned a B.S. in Computer Engineering at Georgia Tech, where I was fortunate to work with Prof. Yao Xie, and a B.S. in Applied Mathematics at Emory University.
Research interests
I work at the intersection of large-scale optimization and machine learning: data-efficient methods for training foundation models, test-time / context memorization, and privacy-preserving learning. Recent work has appeared at ICLR, ICML, and NeurIPS.
Contact
- email
zemanli [at] usc [dot] edu - cvCurriculum Vitae (PDF)
- scholarGoogle Scholar
- githubgithub.com/lizeman
News
- Paper accepted at ICLR 2026 (Spotlight): TNT — Improving Chunkwise Training for Test-Time Memorization.
- Paper accepted at NeurIPS 2026 (Spotlight): PiKE — Adaptive Data Mixing for Multi-Task Learning Under Low Gradient Conflicts.
- Paper accepted at ICML 2025: Synthetic Text Generation for Training Large Language Models via Gradient Matching.
- Paper accepted at ICLR 2025: Addax — Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models.
- Paper accepted at ICML 2024: Optimal Differentially Private Learning with Public Data.
- Started Ph.D. at USC ISE, advised by Prof. Meisam Razaviyayn.
Publications
Auto-synced from Semantic Scholar — last build . ⊕ Atom
9 entries, newest first.
-
Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training
-
Memory Caching: RNNs with Growing Memory
-
Online Neural Space Time Memory for Dynamic Novel View Synthesis
-
PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
-
TNT: Improving Chunkwise Training for Test-Time Memorization
-
Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
-
ATLAS: Learning to Optimally Memorize the Context at Test Time
-
Synthetic Text Generation for Training Large Language Models via Gradient Matching
-
Optimal Differentially Private Model Training with Public Data
Vita
Education
-
Ph.D., Industrial & Systems Engineering, University of Southern California
Advisor: Prof. Meisam Razaviyayn -
B.S., Computer Engineering, Georgia Institute of Technology
Advisor: Prof. Yao Xie - B.S., Applied Mathematics, Emory University
Awards
- USC Viterbi School of Engineering Fellowship
- Georgia Tech Capstone Design Expo — Best Overall Project
- Mathematical Contest in Modeling — Meritorious Winner (top 6.9% of 10,053 teams)
- Mathematical Contest in Modeling — Finalist Award (top 1.3% of 13,753 teams)
- SIMIODE Challenge Using Differential Equations Modeling — Outstanding Winner
Knowledge Base
Working notes I keep while reading — published openly in case someone else finds them useful.
Playground
Some small interactive things I’ve built into this site for fun.