← Back to literature explorer
Instruction-Tuned From survey PDF — verify links

VAU-R1

VAU-R1 — Anomaly Reasoning

arXiv · 2025

Survey summary

VAU-R1 uses reinforcement fine-tuning on MLLMs to improve anomaly reasoning, decomposing understanding into multiple-choice QA, temporal grounding, and reasoning tasks; paired with VAU-Bench, the first chain-of-thought benchmark for video anomaly reasoning with rationales and temporal annotations.

Instruction-Tuned

Instruction-TunedAnomaly Reasoning
Instruction-TunedReinforcement fine-tuningGRPOMulti-task