I work at Huawei Technologies as a research scientist now in Beijing.
I am now working on language identification, machine translation and LLM Agent research. If you are seeking any form of employment opportunity, please feel free to email me at dingjianbang1@huawei.com. We are also hiring interns!
I graduated from School of Intelligence Science and Technology, Peking University (北京大学智能学院) with a master’s degree, supervised by Prof. Zhihong Deng (邓志鸿) and from Qian Xuesen Class, Xidian University (西安电子科技大学钱学森班) with a bachelor’s degree. I also collaborate with Prof. Xu Sun (孙栩) closely.
I won the CCL 2023 Best Poster Award and the Huawei Top-10 Patents Nomination Award (华为终端BG十大发明提名). My work was selected by the Xi’an Municipal Government for exhibition at the 2017 Silk Road International Expo (2017丝绸之路国际博览会). I have published several papers at the premier international AI conferences such as IJCNN, NLPCC and CCL.
🔥 News
- 2024.08: AdaMod optimizer has garnered over 50+ citations and 120+ stars
- 2024.03: One paper is accepted by IJCNN 2024
- 2023.08: 🎉 Win the CCL 2023 best poster award
- 2023.07: One paper is accepted by NLPCC 2023
- 2023.06: One paper is accepted by CCL 2023
📝 Publications
An Adaptive and Momental Bound Method for Stochastic Learning
Jianbang Ding, Xuancheng Ren, Ruixuan Luo, Xu Sun
[Paper] [Code] [Video]
We propose AdaMod , an improvement over the Adam optimizer by adding in a long-term memory aspect.
Just pip install adamod to try it! Up to now, it has multiple several variants and implementations, supporting both Pytorch, Tensorflow, Keras.
![sym](images/nlpcc.jpg)
An Adaptive Learning Method for Solving the Extreme Learning Rate Problem of Transformer
Jianbang Ding, Xuancheng Ren, Ruixuan Luo
[Paper] [Code] [Video]
Conducting more empirical studies on AdaMod.
Some third-party’s Comments:
- “In testing AdaMod on some datasets along with other optimizers, I find that AdaMod is consistently a top 5 optimizer.” ——Less Wright
- “I’ve had great success with this wrapped in lookahead.” ——Evan Walters
Adder Encoder for Pre-trained Language Model
Jianbang Ding, Suiyun Zhang, Linlin Li
[Paper] [Poster]
🎉CCL Best Poster Award
AddderBERT achieves highly competitive performance against that of BERT-base on the GLUE benchmark while obtaining a 4.9x reduction in energy consumption.
Disfluency Detection for Real-World Scenarios
Jianbang Ding, Suiyun Zhang, Dandan Tu
[Paper] [Slide] [Video]
Oral Paper
Our approach significantly outperforms previous baselines and achieves state-of-the-art performance (94.3 F-score) on English Switchboard corpus.
🎖 Honors and Awards
- 2023.12 Huawei Top-10 Patents Nomination Award
- 2023.08 CCL 2023 Best Poster Award
- 2021.06 Outstanding Graduates of Peking University
- 2018.06 Outstanding Graduates of Xidian University
- 2017.09 National Scholarship (Top 1%)
📖 Educations
- 2018.09 - 2021.07, Master, Peking University, Beijing.
- 2014.09 - 2018.07, Bachelor, Xidian University, Xi’an.
- 2010.09 - 2013.07, Northeast Yucai School, Shenyang
💻 Experiences
- 2021.08 - Now, research scientist, Celia Dept, Huawei, Beijing.
- 2020.07 - 2020.09, research intern, Noah’s Ark Lab, Huawei, Beijing.
- 2017.11 - 2018.05, research intern, Qian Xuesen Lab, China Academy of Space Technology, Beijing