Authors

Yucheng Chen

Publications 2

Preprint Open access

PIVOT: Pivot-Aware On Policy Self Distillation for Multi-Turn VLM Agents

Jiazhou Zhou, Hu Zhou, Yucheng Chen et al. · 2026

Reinforcement learning with verifiable rewards (RLVR) via Group-Relative Policy Optimization (GRPO) is widely used for multi-turn VLM agent training, yet it suffers from zero-gradient silence on uniform failures and coarse episode-level credit assignment. While On-Policy Distillation (OPD) and On-Policy Self-Distillati …

Preprint Open access

Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration

Zhiruo Zhou, Rigaudiere Z. Li, Chen Xiwen et al. · 2026

Frozen adaptive cruise control (ACC) policies can violate constraints when deployment dynamics differ from their training conditions. We propose residual-aware conformal action filtering (RACF), which calibrates residuals of a fixed nominal predictor and converts their quantile into an operating margin for finite-model …

Co-authors

Zhiruo Zhou Rigaudiere Z. Li Chen Xiwen Xiaojun Zhu Houde Liu Jiazhou Zhou Hu Zhou Jinyuan Qu Ying-Cong Chen Lei Zhang