VAU-R1 uses Group Relative Policy Optimization with accuracy, format, and temporal-IoU rewards to improve video anomaly reasoning on a new LLM-generated benchmark, VAU-Bench.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
VAU-R1 uses Group Relative Policy Optimization with accuracy, format, and temporal-IoU rewards to improve video anomaly reasoning on a new LLM-generated benchmark, VAU-Bench.