List of Publications

Selected publications are underlined.

^* First author    ^† Co-first author    ^✉ Corresponding author

• Under Submission

  • Doudou Zhang, Wenwen Hou, Yilin Chen, Qi Chen^✉. Learning the Geometry of Drifting Models: Persistent Representations for One-Step Generation.
  • Wenwen Hou, Gezheng Xu, Doudou Zhang, Changjian Shui, Qi Chen^✉. RL Does Not Always Forget Less: Understanding Learning and Retention in LLM Post-Training.
  • Yaohong Yang, Gauri Pradhan, Qi Chen, Samuel Kaski, Antti Honkela. Shift-Aware Score Transport for Privacy Auditing Without Retraining.
  • Yifu Luo, Chuang Ma, Zeyu Chen, Enkelejda Kasneci, Qi Chen, Gjergji Kasneci. Every Token Needs Its Own Teacher: Multi-Teacher Adaptive On-Policy Self-Distillation.
  • Xing Shen, Yifan Qin, Gezheng Xu, Qi Chen, Changjian Shui. Position: Dataset Misuse Risk Evaluation Requires Operationalizing the Burden of Proof.

---

• Thesis (Excellent, placed on Honor List)
  • Qi Chen. [“Theoretical framework for prior knowledge transfer in deep learning”, 2024.][slides]
• Meta Learning, Continual Learning
  • Qi Chen^*✉, Changjian Shui, Ligong Han, and Mario Marchand^✉. On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm. NeurIPS 2023.[Open Review] [Paper] [Code]
  • Qi Chen^*✉, Changjian Shui, Mario Marchand^✉. Generalization Bounds for Meta-Learning: An Information-Theoretic Analysis. NeurIPS 2021. (Spotlight, 3% of submissions) [Open Review][Paper] [Code]
• Bayes Optimization, AI4Science
  • Qi Chen^*✉, Fabio Ramos, Alan Aspuru-Guzik, Florian Shkurti^✉. [Informing Acquisition Functions via Foundation Models for Molecular Discovery.] NeurIPS 2026.
• Generative Models
  • Qi Chen^*✉, Jerry Zhu, Florian Shkurti^✉. Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis. ICLR 2025.[Open Review] [Paper] [Code]
  • Doudou Zhang, Qi Chen^✉. Constrained Look-ahead Guidance for Interference-Aware Flow Editing. NeurIPS 2026.
  • Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, et al. Proxedit: Improving tuning-free real image editing with proximal guidance. WACV 2024.
• Domain Adaptation
  • Gezheng Xu, Qi Chen, Qiuhao Zeng, Charles Ling, Boyu Wang. Discretized Density-Guided Source-Free Adaptation for Continuous Targets. ICML 2026.(Spotlight, 2.2% of submissions)
  • Qi Chen^*, and Mario Marchand^✉. Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation. AISTATS 2023.[Paper] [Code]
  • Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné, and Boyu Wang. A novel domain adaptation theory with Jensen–Shannon divergence. Knowledge-Based Systems, 2022.[Paper]
  • Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné, and Boyu Wang. Beyond H-divergence: Domain Adaptation Theory with Jensen-Shannon Divergence. 2020. [paper]
• Algorithmic Fairness
  • Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui. Intersectional Unfairness Discovery. ICML 2024.
  • Changjian Shui^†, Gezheng Xu^†, Qi Chen, Jiaqi Li, Charles X. Ling, Tal Arbel, Boyu Wang, and Christian Gagné. On learning fairness and accuracy on multiple subgroups. NeurIPS 2022.[Paper]
  • Changjian Shui, Qi Chen, Jiaqi Li, Boyu Wang, and Christian Gagné. Fair Representation Learning through Implicit Path Alignment. ICML 2022. [Paper]
• Sequence Prediction
  • Qiuhao Zeng, Longkai Huang, Qi Chen, Charles Ling, Boyu Wang. Towards Understanding Evolving Patterns in Sequential Data. NeurIPS 2024.