3 papers
cs.CV2026
Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning
Xueheng Li, Yu Wang, Tao Hu +6
Pest-induced crop losses pose a major threat to global food security and sustainable agricultural development. While recent advances in Multimodal Large Language Models (MLLMs) hav…
cs.CV2026
Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion
Ke Cao, Xuanhua He, Tao Hu +3
Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are…
cs.LG2026
When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning
Zheng Zhang, Tao Hu, Xueheng Li +4
Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowledge. Conventional CIL approaches implic…