UIUC Trustworthy ML Lab
- 30 followers
- United States of America
- https://hanzhaoml.github.io/
- hanzhao@illinois.edu
We are a group of researchers from the University of Illinois Urbana-Champaign, working on machine learning research, aiming to push the frontier of machine learning beyond accuracy and efficiency. A list of topics that we are currently working on includes:
- Distributional robustness: domain adaptation, domain generalization, transfer learning
- Algorithmic fairness: group fairness, post-processing algorithms
- Privacy: intersection between fairness, privacy & robustness, machine unlearning
- Explainability: influence function, Shapley values, data attributions,
- Probabilistic circuits: expressiveness, neuro-symbolic models, interpretability
- AI for Science: foundation models for geospatial data
An overview of our group's research:
Pinned Loading
Repositories
- LESSViT Public
LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
-
- convex_data_valuation Public
[ICML '26] Code repo for the paper entitled "Convex Dataset Valuation for Post-Training" at ICML 2026.
- TaskVectorBasis Public
[TMLR] Code repo for the paper entitled Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic"
- ChronoEarth492K Public
ChronoEarth-492K: A Large Scale and Long Horizon Spatiotemporal Hyperspectral Earth Observation Dataset and Benchmark
- AdaOMD-TCH Public
[TMLR] Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learning
Top languages
Loading…
Most used topics
Loading…