5 papers
SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs
Chao Pan, Yu Wu, Xin Yao
Internal Safety Collapse (ISC) is a failure mode in which frontier LLMs, when executing legitimate professional tasks whose correct completion structurally requires harmful content…
Scalable Training of Mixture-of-Experts Models with Megatron Core
Zijie Yan, Hongxiao Bai, Xin Yao +42
Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total pa…
Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams
Yiming Cui, Xin Yao, Yuxuan Qin +3
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, mole…
ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding
Xingqi Wang, Yiming Cui, Xin Yao +3
Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requir…
Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models
Jiajun Li, Tianze Xu, Xuesong Chen +2
In recent years, AI-Generated Content (AIGC) has witnessed rapid advancements, facilitating the creation of music, images, and other artistic forms across a wide range of industrie…