Showing cs.LGShow all
3 papers · 1 filter
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.LG2025
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.LG2025
CALM: Consensus-Aware Localized Merging for Multi-Task Learning
Kunda Yan, Min Zhang, Sen Cui +4
Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task…