Full Professor, Chongqing University of Post and Telecommunications
2 papers at NeurIPS 2025
We introduce A2Seek, a reasoning-centric benchmark for aerial anomaly understanding, and A2Seek-R1, a method designed to seek and interpret anomalies.
This paper proposes a novel AIGI detection method based on Multi-granularity Local Entropy Patterns (MLEP), which captures scale- and location-invariant entropy features to improve accuracy and generalization across diverse generative models.
