王业全是北京人工智能研究院的一位科研团队主管,研究兴趣主要包含大模型 (Large Model) 。他带领
认知模型团队
,旨在构建更低成本但能力更强的大模型,并开展相关的的大模型研究,并最终实现 AGI 的目标。
王业全博士在
朱小燕
教授和
黄民烈
教授的指导下,在清华大学获得计算机科学博士学位。其中,2017年到2018年,在南洋理工大学以访问博士的方式跟随
孙爱欣
教授学习。
2022年,获得2022年全球最具影响力人工智能学者提名奖(自然语言处理)。
2022年11月-2025年11月,主持“新一代人工智能”国家科技重大专项。
大模型研发的团队理念
:
系统能力和科研能力缺一不可
。没有系统能力,就无法研发大模型。没有科研能力,只能亦步亦趋,在大模型领跑者选择闭源的情况下,无法进一步突破。
谷歌学术引用:
3,500+
ORCID:
0000-0001-7530-6125
As scaling laws underscore the potential of increasing model sizes, the academic community has intensified its investigations into LLMs with capacities exceeding 50 billion parameters. This technical report builds on our prior work with Tele-FLM (also known as FLM-2), a publicly available 52-billion-parameter model.
We find that Maximal Update parametrization (uP) enables accurate fitting of scaling laws for hyperparameters close to common loss basins, without any search. Thus, different models can be directly compared on large scales with loss prediction even before the training starts. We propose a new paradigm as a first step towards reliable academic research for any model scale without heavy computation.
(2022).
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction
.
In
COLING 2022
.
(2022).
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict
.
In
Findings of NAACL 2022
.