Publications
Under Review
- D. Zhu, M. Khalili, “WAQS: Weight Absorption for Quadratic Probing and Affine Steering,” under review, 2026. project page paper code
Selected Conference Papers
D. Zhu, X. Wei, T. Xie, Z. Zhu, X. Zhang, M. Khalili, “PORT: Preference Optimization via Robust Token-Level Reweighting,” The Conference on Neural Information Processing Systems (NeurIPS), 2026. project page paper code
S. Gupte, X. Zhang, M. Khalili, “When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs,” The Conference on Language Modeling (COLM), 2026. project page paper code
X. Zhu, M. Khalili, Z. Zhu, “AbsTopK: Rethinking Sparse Autoencoders for Bidirectional Features,” The International Conference on Learning Representations (ICLR), 2026. paper code
X. Zhang, M. Khalili, K. Jin, P. Naghizadeh, M. Liu, “Fairness Interventions as (Dis)incentives for Strategic Manipulation,” The International Conference on Machince Learning (ICML), 2022. link
K. Jin, X. Zhang, M. Khalili, P. Naghizadeh, M. Liu, “Making Cheating Less Appealing: Incentivizing Honesty in Strategic Classification Problems,” The Conference on Economics and Computation (EC), 2022. link
M. Samizadeh, M. Khalili, “Perfectly Fair and Differentially Private Selection Using the Laplace Mechanism,” The ICLR Workshop on Socially Responsible Machine Learning, 2022. link
G. Aminian, M. Abroshan, M. Khalili, “A Theoretical-Inspired Semi-supervised Learning Algorithm under Covariate-shift,” The International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. link
M. Khalili, X. Zhang, M. Abroshan, “Fair Sequential Selection Using Supervised Learning Models,” The Conference on Neural Information Processing Systems (NeurIPS), 2021. link
M. Khalili, X. Zhang, M. Abroshan, S. Sojoudi, “Improving Fairness and Privacy in Selection Problems,” The AAAI Conference on Artificial Intelligence (AAAI), 2021. link
I. Vakilinia, M. Khalili, M. Ling, “A Mechanism Design Approach to Solve Ransomware Dilemmas,” The Conference on Decision and Game Theory for Security (GameSec), 2021. link
Selected Journal Papers
X. Zhu, J. Jiang, M. Khalili, Z. Zhu, “From Emergence to Control: Probing and Modulating Self-Reflection in Language Models,” Transactions on Machine Learning Research (TMLR), 2026. paper code
D. Zhu, Z. Zuo, M. Khalili, “An Efficient Training Algorithm for Models with Block-wise Sparsity,” Transactions on Machine Learning Research (TMLR), 2025. paper code
You can also find my articles on my Google Scholar profile.