collaborators

8 papers

cs.LG2026

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

Zikun Qu, Min Zhang, Mingze Kong +5

On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other pla…

cs.LG2026

Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation

Bo Xue, Zhi Hong, Jiayi Li +3

Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives. In this paper, we formulate…

cs.LG2026

Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits

Bo Xue, Ji Cheng, Haodong Jing +2

This paper studies generalized low-rank matrix bandits with multiple prioritized objectives. At each round, the learner selects a matrix-valued arm and observes a vector-valued rew…

cs.LG2026

DemoPSD: Disagreement-Modulated Policy Self-Distillation

Yunhe Li, Hao Shi, Wenhao Liu +5

On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the stud…

cs.LG2026

T-POP: Test-Time Personalization with Online Preference Feedback

Zikun Qu, Min Zhang, Mingze Kong +7

Personalizing large language models (LLMs) to individual user preferences is a critical step beyond generating generically helpful responses. However, current personalization metho…

cs.AI2026

Learning to Reason with Insight for Informal Theorem Proving

Yunhe Li, Hao Shi, Bowen Deng +8

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in n…