Sample Publications (Show All)

• Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection
  (with Addison Kristanto Julistiono and Navid Azizan)
  JMLR 2026
  Code
• Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
  (with Zhuoping Zhou, Sima Didari, Wenjun Hu, Baruch Gutow, Oxana Verkholyak, Masoud Faraki, Heng Hao, Hankyu Moon, and Seungjai Min)
  ICLR 2026
  
• Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
  (with Parvin Nazari, Bojian Hou, Li Shen, and George Michailidis)
  NeurIPS 2025
  Slides Poster Code
• Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
  (with Yingcong Li, Ankit Singh Rawat, Maryam Fazel, and Samet Oymak)
  COLM 2025
  Poster
• Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods
  (with Parvin Nazari, Bojian Hou, Li Shen, and Laura Balzano)
  AISTATS 2024
  Poster Code
• Fairness-Aware Estimation of Graphical Models
  (with Zhuoping Zhou, Bojian Hou, Qi Long, and Li Shen)
  NeurIPS 2024
  Code
• Max-Margin Token Selection in Attention Mechanism
  (with Yingcong Li, Xuechen Zhang, and Samet Oymak)
  NeurIPS 2023 Spotlight
  Slides Code
  
• Fair Canonical Correlation Analysis
  (with Zhuoping Zhou, Bojian Hou, Boning Tong, Jia Xu, Yanbo Feng, Qi Long, and Li Shen)
  NeurIPS 2023
  Slides Poster Code
• Transformers as Support Vector Machines
  (with Yingcong Li, Christos Thrampoulidis, and Samet Oymak)
  NeurIPS M3L Workshop 2023
  Slides Poster Code
• FedNest: Federated Bilevel, Minimax, and Compositional Optimization
  (with Mingchen Li, Christos Thrampoulidis, and Samet Oymak)
  ICML 2022 Oral
  Slides Code