Zhaolu Kang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces PriceBlind, a white-box adversarial attack framework that demonstrates how imperceptible visual perturbations can trick multimodal agents into ignoring textual price constraints during financial transactions.
SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon tool use.
Papers
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering
Qiming Shi, Zhaolu Kang, Yunfan Zhou, Di Weng +1 more
SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon…