4 papers · 1 filter
Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation
Jianghao Wang, Ke Meng, Jian Li +7
Omni-modal large language models (OmniLLMs) enable unified audio-video understanding, but their long multimodal token sequences make deployment computationally expensive. Token com…
RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation
Yiyang Zou, Tianhao Zhao, Peilun Xiao +9
Accident anticipation aims to predict impending collisions from dashcam videos and trigger early alerts. Existing methods rely on binary supervision with manually annotated "anomal…
Accident Anticipation via Temporal Occurrence Prediction
Tianhao Zhao, Yiyang Zou, Zihao Mao +7
Accident anticipation aims to predict potential collisions in an online manner, enabling timely alerts to enhance road safety. Existing methods typically predict frame-level risk s…
Penalizing Boundary Activation for Object Completeness in Diffusion Models
Haoyang Xu, Tianhao Zhao, Sibei Yang +1
Diffusion models have emerged as a powerful technique for text-to-image (T2I) generation, creating high-quality, diverse images across various domains. However, a common limitation…