Zobrazeno 1 - 10
of 1 307
pro vyhledávání: '"Han, Jiawei"'
Autor:
Xu, Zexing, Zhang, Linjun, Yang, Sitan, Etesami, Rasoul, Tong, Hanghang, Zhang, Huan, Han, Jiawei
Demand prediction is a crucial task for e-commerce and physical retail businesses, especially during high-stake sales events. However, the limited availability of historical data from these peak periods poses a significant challenge for traditional f
Externí odkaz:
http://arxiv.org/abs/2406.16221
Socratic questioning is an effective teaching strategy, encouraging critical thinking and problem-solving. The conversational capabilities of large language models (LLMs) show great potential for providing scalable, real-time student guidance. Howeve
Externí odkaz:
http://arxiv.org/abs/2406.11709
In many scientific fields, large language models (LLMs) have revolutionized the way with which text and other modalities of data (e.g., molecules and proteins) are dealt, achieving superior performance in various applications and augmenting the scien
Externí odkaz:
http://arxiv.org/abs/2406.10833
Self-correction is an approach to improving responses from large language models (LLMs) by refining the responses using LLMs during inference. Prior work has proposed various self-correction frameworks using different sources of feedback, including s
Externí odkaz:
http://arxiv.org/abs/2406.01297
Logical reasoning task has attracted great interest since it was proposed. Faced with such a task, current competitive models, even large language models (e.g., ChatGPT and PaLM 2), still perform badly. Previous promising LMs struggle in logical cons
Externí odkaz:
http://arxiv.org/abs/2405.19109
Knowledge Graph Embedding (KGE) techniques are crucial in learning compact representations of entities and relations within a knowledge graph, facilitating efficient reasoning and knowledge discovery. While existing methods typically focus either on
Externí odkaz:
http://arxiv.org/abs/2405.16412
Autor:
Zhu, Jinfu, Ding, Hongli, Li, Haokui, Ran, Qiaoye, Dai, Xiwen, Li, Wei, Han, Jiawei, Li, Yue, Zhang, Zhiyuan, Qiu, Weixin, Zhang, Weiqing
Many accelerators require considerable electronic systems for tests, verification, and operation. In Shenzhen Superconducting Soft X-ray Free Electron Laser (S3FEL), to meet the early tests and verification of various systems, save development expens
Externí odkaz:
http://arxiv.org/abs/2406.15407
Despite widespread applications of knowledge graphs (KGs) in various tasks such as question answering and intelligent conversational systems, existing KGs face two major challenges: information granularity and deficiency in timeliness. These hinder c
Externí odkaz:
http://arxiv.org/abs/2404.19146
Autor:
Qu, Yanru, Qiu, Keyue, Song, Yuxuan, Gong, Jingjing, Han, Jiawei, Zheng, Mingyue, Zhou, Hao, Ma, Wei-Ying
Generative models for structure-based drug design (SBDD) have shown promising results in recent years. Existing works mainly focus on how to generate molecules with higher binding affinity, ignoring the feasibility prerequisites for generated 3D pose
Externí odkaz:
http://arxiv.org/abs/2404.12141
Autor:
Jin, Bowen, Xie, Chulin, Zhang, Jiawei, Roy, Kashob Kumar, Zhang, Yu, Wang, Suhang, Meng, Yu, Han, Jiawei
Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora t
Externí odkaz:
http://arxiv.org/abs/2404.07103