Research

✉ corresponding author · † equal contribution

Preprints & Under Review

Informing Acquisition Functions via Foundation Models for Molecular Discovery
Qi Chen✉, Fabio Ramos, Alan Aspuru-Guzik, Florian Shkurti✉
arXiv preprint  ·  2025
arXiv
bayesian-optimization ai-for-science foundation-models
Constrained Look-ahead Guidance for Interference-Aware Flow Editing
Doudou Zhang, Qi Chen✉
Under review
generative-models flow-models
Position: Dataset Misuse Risk Evaluation Requires Operationalizing the Burden of Proof
Xing Shen, Yifan Qin, Gezheng Xu, Qi Chen, Changjian Shui
Under review
trustworthy-ai

Selected Publications

Discretized Density-Guided Source-Free Adaptation for Continuous Targets
Gezheng Xu, Qi Chen, Qiuhao Zeng, Charles Ling, Boyu Wang
ICML 2026 (Spotlight, 2.2%)  ·  2026
domain-adaptation
Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
Qi Chen✉, Jerry Zhu, Florian Shkurti✉
ICLR 2025  ·  2025
OpenReview
Paper
Code
generative-models learning-theory
Intersectional Unfairness Discovery
Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui
ICML 2024  ·  2024
algorithmic-fairness
On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
Qi Chen✉, Changjian Shui, Ligong Han, Mario Marchand✉
NeurIPS 2023  ·  2023
OpenReview
Paper
Code
continual-learning meta-learning learning-theory
Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
Qi Chen, Mario Marchand✉
AISTATS 2023  ·  2023
Paper
Code
domain-adaptation learning-theory
On Learning Fairness and Accuracy on Multiple Subgroups
Changjian Shui†, Gezheng Xu†, Qi Chen, Jiaqi Li, Charles X. Ling, Tal Arbel, Boyu Wang, Christian Gagné
NeurIPS 2022  ·  2022
Paper
algorithmic-fairness
Generalization Bounds for Meta-Learning: An Information-Theoretic Analysis
Qi Chen✉, Changjian Shui, Mario Marchand✉
NeurIPS 2021 (Spotlight, 3%)  ·  2021
OpenReview
arXiv
Code
meta-learning learning-theory

Support

Our research is supported by the ELLIS Institute Finland, Aalto University and the Helsinki Institute for Information Technology (HIIT). We gratefully acknowledge computational resources provided by the Aalto Triton cluster, CSC – IT Center for Science, and the LUMI supercomputer.

ELLIS Institute FinlandELLIS Institute Finland Aalto UniversityAalto University Helsinki Institute for Information TechnologyHIIT Aalto Scientific ComputingTriton (Aalto Scientific Computing) CSC – IT Center for ScienceCSC LUMI supercomputerLUMI

All Publications

2026

Discretized Density-Guided Source-Free Adaptation for Continuous Targets
Gezheng Xu, Qi Chen, Qiuhao Zeng, Charles Ling, Boyu Wang
ICML 2026 (Spotlight, 2.2%)  ·  2026

2025

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
Qi Chen✉, Jerry Zhu, Florian Shkurti✉
ICLR 2025  ·  2025

2024

Towards Understanding Evolving Patterns in Sequential Data
Qiuhao Zeng, Longkai Huang, Qi Chen, Charles Ling, Boyu Wang
NeurIPS 2024  ·  2024
Intersectional Unfairness Discovery
Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui
ICML 2024  ·  2024
Theoretical Framework for Prior Knowledge Transfer in Deep Learning
Qi Chen
Ph.D. thesis, Laval University (Excellent, Honor List)  ·  2024
ProxEdit: Improving Tuning-Free Real Image Editing with Proximal Guidance
Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, et al.
WACV 2024  ·  2024

2023

On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
Qi Chen✉, Changjian Shui, Ligong Han, Mario Marchand✉
NeurIPS 2023  ·  2023
Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
Qi Chen, Mario Marchand✉
AISTATS 2023  ·  2023

2022

On Learning Fairness and Accuracy on Multiple Subgroups
Changjian Shui†, Gezheng Xu†, Qi Chen, Jiaqi Li, Charles X. Ling, Tal Arbel, Boyu Wang, Christian Gagné
NeurIPS 2022  ·  2022
A Novel Domain Adaptation Theory with Jensen–Shannon Divergence
Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné, Boyu Wang
Knowledge-Based Systems  ·  2022
Fair Representation Learning through Implicit Path Alignment
Changjian Shui, Qi Chen, Jiaqi Li, Boyu Wang, Christian Gagné
ICML 2022  ·  2022

2021

Generalization Bounds for Meta-Learning: An Information-Theoretic Analysis
Qi Chen✉, Changjian Shui, Mario Marchand✉
NeurIPS 2021 (Spotlight, 3%)  ·  2021

2020

Beyond H-Divergence: Domain Adaptation Theory with Jensen-Shannon Divergence
Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné, Boyu Wang
arXiv preprint  ·  2020