collaborators

10 papers

cs.LG2026

Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability

Yushen Liu, Yin-Jen Chen, Ziyi Chen +4

Many safety-critical control problems are modeled as risk-sensitive partially observable Markov decision processes, where the controller must make decisions from incomplete observa…

cs.CL2026

SOMA: Efficient Multi-turn LLM Serving via Small Language Model

Xueqi Cheng, Qiong Wu, Zhengyi Zhou +3

Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential. A standard serving practic…

cs.CL2026

ReAD: Reinforcement-Guided Capability Distillation for Large Language Models

Xueqi Cheng, Xugui Zhou, Tyler Derr +1

Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abili…

cs.CR2026

Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)

Taibiao Zhao, Xiang Zhang, Mingxuan Sun +2

Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips…

cs.LG2026

Integrating Neural Differential Forecasting with Safe Reinforcement Learning for Blood Glucose Regulation

Yushen Liu, Yanfu Zhang, Xugui Zhou

Automated insulin delivery for Type 1 Diabetes must balance glucose control and safety under uncertain meals and physiological variability. While reinforcement learning (RL) enable…

cs.CR2025

KnowSafe: Combined Knowledge and Data Driven Hazard Mitigation in Artificial Pancreas Systems

Xugui Zhou, Maxfield Kouzel, Chloe Smith +1

Significant progress has been made in anomaly detection and run-time monitoring to improve the safety and security of cyber-physical systems (CPS). However, less attention has been…