5 papers
MonitorVLM-v2: A Deployed Vision-Language Framework for Real-Time Safety Violation Detection
Jiang Wu, Sichao Wu, Yinsong Ma +2
Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) approach is poorly suited to sa…
MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations
Jiang Wu, Sichao Wu, Yinsong Ma +4
Industrial accidents, particularly in high-risk domains such as surface and underground mining, are frequently caused by unsafe worker behaviors. Traditional manual inspection rema…
TransMPC: Transformer-based Explicit MPC with Variable Prediction Horizon
Sichao Wu, Jiang Wu, Xingyu Cao +6
Traditional online Model Predictive Control (MPC) methods often suffer from excessive computational complexity, limiting their practical deployment. Explicit MPC mitigates online c…
Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators
Xitao Li, Haijun Wang, Jiang Wu +1
Conversational large language models (LLMs) have gained widespread attention due to their instruction-following capabilities. To ensure conversational LLMs follow instructions, rol…
Diffusion Actor-Critic with Entropy Regulator
Yinuo Wang, Likun Wang, Yuxuan Jiang +8
Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically…