7 citations · 7 across the 5 of their papers we have counts for
3 papers · 1 filter
Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models
Ziyuan Yang, Wenxuan Ding, Shangbin Feng +1
Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As mixture-of-experts (MoE) VLMs…
Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems
Ziyuan Yang, Wenxuan Ding, Shangbin Feng +1
Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and…
MoCo: A One-Stop Shop for Model Collaboration Research
Shangbin Feng, Yuyang Bai, Ziyuan Yang +17
Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, an…