4 papers
OISD: On-Policy Internal Self-Distillation of Language Models
Xinyu Liu, Darryl Cherian Jacob, Yang Zhou +2
Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, while largely overlooking predictive sign…
COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection
Darryl Cherian Jacob, Xinyu Liu, Kai Wang +1
Vision-language models (VLMs) have shown strong performance in video anomaly detection (VAD) while providing interpretable predictions. However, existing VLM-based VAD methods suff…
OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control
Darryl Jacob, Xinyu Liu, Muchao Ye +2
Transparent decision-making is essential for traffic signal control (TSC) systems to earn public trust. However, traditional reinforcement learning-based TSC methods function as bl…
Understanding Real-World Traffic Safety through RoadSafe365 Benchmark
Xinyu Liu, Darryl C. Jacob, Yuxin Liu +4
Although recent traffic benchmarks have advanced multimodal data analysis, they generally lack systematic evaluation aligned with official safety standards. To fill this gap, we in…