Publication record

Publications in learning, optimization, and networked systems.

Search and filter the complete record by type, topic, year, or status. Student authors are underlined, Ming Shi is bolded, and available paper and DOI links are included.

32 works shown

JavaScript adds search, filtering, and citation-copying. The full publication list remains visible without it.

Conference paper2026ICLR

Barriers to Pareto Steerability in Preference-Conditioned LLM Alignment

Fatemeh Nourzad, Daouda Sow, Yingbin Liang, Ming Shi , Ming Zhang, Yunxuan Li, Eylem Ekici, Ness Shroff

14th International Conference on Learning Representations (I Can't Believe It's Not Better: Challenges in Applied Deep Learning), Rio de Janeiro, Brazil, April 2026. [ICLR]

Preferences & multi-objectiveGenerative AI
↗ PDF
Conference paper2023ICLR (Spotlight, with acceptance rate 8.0%.)

Near-Optimal Adversarial Reinforcement Learning with Switching Costs

Ming Shi , Yingbin Liang, and Ness Shroff

11th International Conference on Learning Representations, Kigali, Rwanda, May 2023. [ICLR] (Spotlight, with acceptance rate 8.0%.)

Safety & reliabilityResource adaptationReinforcement learning
↗ PDF
Conference paper2022ACM MobiHoc (Acceptance rate: 19.8%.)

Power-of-2-Arms for Bandit Learning with Switching Costs

Ming Shi , Xiaojun Lin, and Lei Jiao

23rd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, Seoul, South Korea, October 2022. [ACM MobiHoc] (Acceptance rate: 19.8%.)

Resource adaptationBandit learningNetworked systems
↗ PDF

Student authors: student names from the existing publication page are underlined. Status note: entries labeled “submitted” are retained exactly as provided; review those statuses before deployment because several refer to 2026 venues.