3 papers
eess.IV2026
CAMAL: Improving Attention Alignment and Faithfulness with Segmentation Masks
Rajdeep Singh Hundal, Yan Xiao, Jin Song Dong +1
Many vision datasets now provide segmentation masks in addition to annotated images to support a wide range of tasks. In this work, we propose Class Activation Map Attention Learni…
cs.SE2025
On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations
Rajdeep Singh Hundal, Yan Xiao, Xiaochun Cao +2
Deep Reinforcement Learning (DRL) is a paradigm of artificial intelligence where an agent uses a neural network to learn which actions to take in a given environment. DRL has recen…
cs.CR2025
Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
Wenqiang Wang, Yan Xiao, Hao Lin +2
Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attack…