2 papers
cs.LG2026
Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
Ming Wen, Kun Yang, Xin Chen +4
Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently gen…
cs.CR2025
Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix
Ming Wen, Jiaqi Zhu, Yuedong Xu +2
Large language models (LLMs) typically require fine-tuning for domain-specific tasks, and LoRA offers a computationally efficient approach by training low-rank adapters. LoRA is al…