Anomalous video understanding aims to identify abnormal events in videos and interpret their semantic meanings beyond simple anomaly detection. Recent video large language models (Video-LLMs) have demonstrated promising zero-shot capabilities for this task, yet their performance remains limited due to insufficient adap...
Hui-Ning Li, Yu-Xiang Duan, Ji-Yang Tan et al.· 0 citations
Calibrated On-Policy Distillation is introduced, which estimates the teacher's self-deviation region through positive and negative privileged interventions and calibrates the original teacher--student discrepancy by retaining only the component that lies beyond this region.
Qiang-Qiang He, Jin Li, Ming-Cai Chen· 2 citations· ⚡1
Vision-language models often use descriptions of earlier visual states to make decisions about the current scene. When the scene changes, stale language can redirect an otherwise correct visual judgment toward an outdated answer. We study this failure as visual lock-in in a controlled grounding setting where only the v...
VITAL-RAG is introduced, which organizes evidence by canonical code object, keeps one query-relevant companion only when it adds semantics not already represented, and renders selected evidence under per-object and global token budgets.
