3 citations · 9 across the 10 of their papers we have counts for
4 papers · 1 filter
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
Zhongxi Wang, Yueqian Lin, Jingyang Zhang +3
Safety evaluation of multimodal large language models requires tracking not only whether an attack succeeds, but also how the interaction unfolds across turns and input modalities.…
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
Yudong Liu, Jingwei Sun, Yueqian Lin +6
Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to red…
FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning
Minxue Tang, Yitu Wang, Jingyang Zhang +5
Federated Adversarial Training (FAT) can supplement robustness against adversarial examples to Federated Learning (FL), promoting a meaningful step toward trustworthy AI. However,…
Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency
Bhavna Gopal, Huanrui Yang, Jingyang Zhang +2
Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an inno…