Research
Research Interests
I am broadly interested in building intelligent systems that learn, decide, and optimize in complex, real-world environments. My current research spans deep learning for ranking and recommendation, multi-objective and constrained optimization, large language models for information retrieval and reasoning, uncertainty quantification, and online decision making.
More broadly, I work on stochastic optimization, optimal transport, robustness and reliability of deep learning, reinforcement learning and bandits, and neural architecture search.
I'm always open to collaboration and happy to chat — feel free to reach out via email.
Full list also on Google Scholar. ("*" indicates equal contribution)
2026
- Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning.
Peihao Wang, Shan Yang, Xijun Wang, Tesi Xiao, Xin Liu, Changlong Yu, Yu Lou, Pan Li, Zhangyang Wang, Ming Lin. ICML 2026.
[arXiv] [code]
2025
- COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework.
Yinuo Ren, Tesi Xiao, Michael Shavlovsky, Lexing Ying, Holakou Rahmanian. UAI 2025.
[paper] [arXiv] [code]
Early version: HyperDPO: Hypernetwork-based Multi-Objective Fine-Tuning Framework, NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning. [workshop] - Orbit: A Framework for Designing and Evaluating Multi-objective Rankers.
Chenyang Yang, Tesi Xiao*, Michael Shavlovsky*, Christian Kästner, Tongshuang Wu. IUI 2025.
[paper] [arXiv] [slides] - RewardRank: Optimizing True Learning-to-Rank Utility.
Gaurav Bhatt, Kiran Koshy Thekumparampil, Tanmay Gangwani, Tesi Xiao, Leonid Sigal. Preprint, 2025.
[arXiv] - An Efficient Algorithm for Entropic Optimal Transport under Martingale-type Constraints.
Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Tesi Xiao, Lexing Ying. Preprint, 2025.
[arXiv]
2024
- Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions.
Xuxing Chen*, Tesi Xiao*, Krishnakumar Balasubramanian. JMLR 2024.
[paper] - Accelerating Sinkhorn Algorithm with Sparse Newton Iterations.
Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Elisa Tardini, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying. ICLR 2024.
[paper] - Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow.
Yinuo Ren, Tesi Xiao, Tanmay Gangwani, Anshuka Rangi, Holakou Rahmanian, Lexing Ying, Subhajit Sanyal. AISTATS 2024.
[paper] [code] [poster] - A Sinkhorn-type Algorithm for Constrained Optimal Transport.
Xun Tang, Holakou Rahmanian, Michael Shavlovsky, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying. ArXiv preprint.
[paper]
2023
- A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization.
Tesi Xiao*, Xuxing Chen*, Krishnakumar Balasubramanian, Saeed Ghadimi. UAI 2023.
[paper] [poster] - Towards Sequential Counterfactual Learning to Rank.
Tesi Xiao, Branislav Kveton, Sumeet Katariya, Tanmay Gangwani, Anshuka Rangi. SIGIR-AP 2023.
[paper]
2022
- A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization.
Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi. NeurIPS 2022.
[paper] [poster] - Field-wise Embedding Size Search via Structural Hard Auxiliary Mask Pruning for Click-Through Rate Prediction.
Tesi Xiao, Xia Xiao, Ming Chen, Youlong Cheng. CIKM DL4SR Workshop 2022.
[paper]
2020 & Earlier
- How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework.
Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, Cho-Jui Hsieh. CVPR 2020.
[paper]
Early version: Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise, arXiv 2019. [arXiv] - Improved Complexities for Stochastic Conditional Gradient Methods under Interpolation-like Conditions.
Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi. Operations Research Letters.
[paper] - Statistical Inference for Polyak-Ruppert Averaged Stochastic Zeroth-order Gradient Algorithm.
Yanhao Jin*, Tesi Xiao*, Krishnakumar Balasubramanian. ArXiv preprint, 2021.
[paper]
Optimization
- COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework.
Yinuo Ren, Tesi Xiao, Michael Shavlovsky, Lexing Ying, Holakou Rahmanian. UAI 2025.
[paper] [arXiv] [code]
Early version: HyperDPO: Hypernetwork-based Multi-Objective Fine-Tuning Framework, NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning. [workshop] - Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions.
Xuxing Chen*, Tesi Xiao*, Krishnakumar Balasubramanian. JMLR 2024.
[paper] - Accelerating Sinkhorn Algorithm with Sparse Newton Iterations.
Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Elisa Tardini, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying. ICLR 2024.
[paper] - Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow.
Yinuo Ren, Tesi Xiao, Tanmay Gangwani, Anshuka Rangi, Holakou Rahmanian, Lexing Ying, Subhajit Sanyal. AISTATS 2024.
[paper] [code] [poster] - An Efficient Algorithm for Entropic Optimal Transport under Martingale-type Constraints.
Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Tesi Xiao, Lexing Ying. Preprint, 2025.
[arXiv] - A Sinkhorn-type Algorithm for Constrained Optimal Transport.
Xun Tang, Holakou Rahmanian, Michael Shavlovsky, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying. ArXiv preprint.
[paper] - A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization.
Tesi Xiao*, Xuxing Chen*, Krishnakumar Balasubramanian, Saeed Ghadimi. UAI 2023.
[paper] [poster] - A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization.
Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi. NeurIPS 2022.
[paper] [poster] - Improved Complexities for Stochastic Conditional Gradient Methods under Interpolation-like Conditions.
Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi. Operations Research Letters.
[paper] - Statistical Inference for Polyak-Ruppert Averaged Stochastic Zeroth-order Gradient Algorithm.
Yanhao Jin*, Tesi Xiao*, Krishnakumar Balasubramanian. ArXiv preprint.
[paper]
Recommender Systems & Ranking
- RewardRank: Optimizing True Learning-to-Rank Utility.
Gaurav Bhatt, Kiran Koshy Thekumparampil, Tanmay Gangwani, Tesi Xiao, Leonid Sigal. Preprint, 2025.
[arXiv] - Orbit: A Framework for Designing and Evaluating Multi-objective Rankers.
Chenyang Yang, Tesi Xiao*, Michael Shavlovsky*, Christian Kästner, Tongshuang Wu. IUI 2025.
[paper] [arXiv] [slides] - Towards Sequential Counterfactual Learning to Rank.
Tesi Xiao, Branislav Kveton, Sumeet Katariya, Tanmay Gangwani, Anshuka Rangi. SIGIR-AP 2023.
[paper] - Field-wise Embedding Size Search via Structural Hard Auxiliary Mask Pruning for Click-Through Rate Prediction.
Tesi Xiao, Xia Xiao, Ming Chen, Youlong Cheng. CIKM DL4SR Workshop 2022.
[paper]
Deep Learning
- Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning.
Peihao Wang, Shan Yang, Xijun Wang, Tesi Xiao, Xin Liu, Changlong Yu, Yu Lou, Pan Li, Zhangyang Wang, Ming Lin. ICML 2026.
[arXiv] [code] - How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework.
Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, Cho-Jui Hsieh. CVPR 2020.
[paper]
Early version: Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise, arXiv 2019. [arXiv]