15 citations · 36 across the 18 of their papers we have counts for
7 papers · 1 filter
A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
Ye Yuan, Chengwu Liu, Jingyang Yuan +3
Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge base…
AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
Bo-Wen Zhang, Liangdong Wang, Ye Yuan +24
In recent years, with the rapid application of large language models across various fields, the scale of these models has gradually increased, and the resources required for their…
Vision-Braille: A Curriculum Learning Toolkit and Braille-Chinese Corpus for Braille Translation
Alan Wu, Ye Yuan, Zhiping Xiao +1
We present Vision-Braille, the first publicly available end-to-end system for translating Chinese Braille extracted from images into written Chinese. This system addresses the uniq…
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation
Jinsheng Huang, Liang Chen, Taian Guo +13
Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image,…
Measuring Social Norms of Large Language Models
Ye Yuan, Kexin Tang, Jianhao Shen +2
We present a new challenge to examine whether large language models understand social norms. In contrast to existing datasets, our dataset requires a fundamental understanding of s…
Preparing Lessons for Progressive Training on Language Models
Yu Pan, Ye Yuan, Yichun Yin +6
The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior…
Measuring Vision-Language STEM Skills of Neural Models
Jianhao Shen, Ye Yuan, Srbuhi Mirzoyan +2
We introduce a new challenge to test the STEM skills of neural models. The problems in the real world often require solutions, combining knowledge from STEM (science, technology, e…