4 papers
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…
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…
Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction
Mingze Kong, Zikun Qu, Zhongquan Zhou +7
The rapid evolution of agentic workflows has demonstrated strong performance of LLM-based agents in addressing complex reasoning tasks. However, existing workflow optimization meth…
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…