Zobrazeno 1 - 10
of 1 015
pro vyhledávání: '"Xie, Tong"'
Exploring the predictive capabilities of language models in material science is an ongoing interest. This study investigates the application of language model embeddings to enhance material property prediction in materials science. By evaluating vari
Externí odkaz:
http://arxiv.org/abs/2410.16165
Autor:
Yang, Zonglin, Liu, Wanhao, Gao, Ben, Xie, Tong, Li, Yuqiang, Ouyang, Wanli, Poria, Soujanya, Cambria, Erik, Zhou, Dongzhan
Scientific discovery contributes largely to human society's prosperity, and recent progress shows that LLMs could potentially catalyze this process. However, it is still unclear whether LLMs can discover novel and valid hypotheses in chemistry. In th
Externí odkaz:
http://arxiv.org/abs/2410.07076
Autor:
Zhang, Di, Wu, Jianbo, Lei, Jingdi, Che, Tong, Li, Jiatong, Xie, Tong, Huang, Xiaoshui, Zhang, Shufei, Pavone, Marco, Li, Yuqiang, Ouyang, Wanli, Zhou, Dongzhan
This paper presents an advanced mathematical problem-solving framework, LLaMA-Berry, for enhancing the mathematical reasoning ability of Large Language Models (LLMs). The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to
Externí odkaz:
http://arxiv.org/abs/2410.02884
Autor:
Wan, Yuwei, Liu, Yixuan, Ajith, Aswathy, Grazian, Clara, Hoex, Bram, Zhang, Wenjie, Kit, Chunyu, Xie, Tong, Foster, Ian
We introduce SciQAG, a novel framework for automatically generating high-quality science question-answer pairs from a large corpus of scientific literature based on large language models (LLMs). SciQAG consists of a QA generator and a QA evaluator, w
Externí odkaz:
http://arxiv.org/abs/2405.09939
Autor:
Ye, Yanpeng, Ren, Jie, Wang, Shaozhou, Wan, Yuwei, Wang, Haofen, Razzak, Imran, Hoex, Bram, Xie, Tong, Zhang, Wenjie
Knowledge in materials science is widely dispersed across extensive scientific literature, posing significant challenges for efficient discovery and integration of new materials. Traditional methods, often reliant on costly and time-consuming experim
Externí odkaz:
http://arxiv.org/abs/2404.03080
Stochastic computing (SC) has emerged as a promising computing paradigm for neural acceleration. However, how to accelerate the state-of-the-art Vision Transformer (ViT) with SC remains unclear. Unlike convolutional neural networks, ViTs introduce no
Externí odkaz:
http://arxiv.org/abs/2402.12820
Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks. While prior research has established quantifiable links between model output and training d
Externí odkaz:
http://arxiv.org/abs/2401.09031
Autor:
Xie, Tong, Wan, Yuwei, Huang, Wei, Yin, Zhenyu, Liu, Yixuan, Wang, Shaozhou, Linghu, Qingyuan, Kit, Chunyu, Grazian, Clara, Zhang, Wenjie, Razzak, Imran, Hoex, Bram
Emerging tools bring forth fresh approaches to work, and the field of natural science is no different. In natural science, traditional manual, serial, and labour-intensive work is being augmented by automated, parallel, and iterative processes driven
Externí odkaz:
http://arxiv.org/abs/2308.13565
Autor:
Xie, Tong, Wan, Yuwei, Huang, Wei, Zhou, Yufei, Liu, Yixuan, Linghu, Qingyuan, Wang, Shaozhou, Kit, Chunyu, Grazian, Clara, Zhang, Wenjie, Hoex, Bram
The amount of data has growing significance in exploring cutting-edge materials and a number of datasets have been generated either by hand or automated approaches. However, the materials science field struggles to effectively utilize the abundance o
Externí odkaz:
http://arxiv.org/abs/2304.02213
Autor:
Xie, Tong, Wan, Yuwei, Li, Weijian, Linghu, Qingyuan, Wang, Shaozhou, Cai, Yalun, Liu, Han, Kit, Chunyu, Grazian, Clara, Hoex, Bram
The material science literature contains up-to-date and comprehensive scientific knowledge of materials. However, their content is unstructured and diverse, resulting in a significant gap in providing sufficient information for material design and sy
Externí odkaz:
http://arxiv.org/abs/2212.02805