11 papers
Triaging Threats to Specialized Guardrails
Wenjie Jacky Mo, Xiaofei Wen, Rui Cai +6
Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains challenging because safety ris…
When Vision Speaks for Sound
Xiaofei Wen, Wenjie Jacky Mo, Xingyu Fu +6
Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate…
ModelLens: Finding the Best for Your Task from Myriads of Models
Rui Cai, Weijie Jacky Mo, Xiaofei Wen +5
The open-source model ecosystem now contains hundreds of thousands of pretrained models, yet picking the best model for a new dataset is increasingly infeasible: new models and unb…
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
Qiyao Ma, Dechen Gao, Rui Cai +4
Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing d…
Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
Wenhui Zhu, Xuanzhao Dong, Xiwen Chen +7
The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled pri…
Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
Daiwei Chen, Zhoutong Fu, Chengming Jiang +12
Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in generative recommendation. The standar…