I'm a Senior Research Scientist at Google Deepmind (GDM). I received my PhD degree from the Department of Computer Science at Cornell University in 2022, advised by Prof. Carla P. Gomes. I received my Bachelor's degree in 2017 from Shanghai Jiao Tong University, where I spent four years in ACM Class. I am interested in the general areas of machine learning and language technology, with research focuses on sequence representation learning and probabilistic modeling, often under scenarios with low-supervision. I have developed scalable and general machine learning methods for real-world problems including automatic speech recognition, climate change and scientific discovery. My full CV can be found here.
* denotes equal contribution.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation
Wen Wu, Bo Li, Chao Zhang, Chung-Cheng Chiu, Qiujia Li, Junwen Bai, Tara N Sainath, Philip C Woodland
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
Junwen Bai, Bo Li, Qiujia Li, Tara N. Sainath, Trevor Strohman
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
Tao Lei, Junwen Bai, Siddhartha Brahma, Joshua Ainslie, Kenton Lee, Yanqi Zhou, Nan Du, Vincent Y. Zhao, Yuexin Wu, Bo Li, Yu Zhang, Ming-Wei Chang
Advances In Neural Information Processing Systems (NeurIPS), 2023.
Efficient Domain Adaptation for Speech Foundation Models
Bo Li, Dongseong Hwang, Zhouyuan Huo, Junwen Bai, Guru Prakash, Tara N. Sainath, Khe Chai Sim, Yu Zhang, Wei Han, Trevor Strohman, Francoise Beaufays.
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
Xtal2DoS: Attention-based Crystal to Sequence Learning for Density of States Prediction
Junwen Bai, Yuanqi Du, Yingheng Wang, Shufeng Kong, John Gregoire, Carla Gomes
NeurIPS Workshop on AI for Science, 2022.
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
Junwen Bai, Shufeng Kong, Carla Gomes
International Conference on Machine Learning (ICML), 2022.
A workshop version was presented at NeurIPS Workshop on Deep Generative Models and Downstream Applications, 2021.
Joint Unsupervised and Supervised Training for Multilingual ASR
Junwen Bai, Bo Li, Yu Zhang, Ankur Bapna, Nikhil Siddhartha, Khe Chai Sim, Tara N. Sainath
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022.
Joshua Fan*, Junwen Bai*, Zhiyun Li*, Ariel Ortiz-Bobea, Carla Gomes
AAAI Conference on Artificial Intelligence (AAAI), 2022.
A workshop version won Best ML Innovation Paper award at NeurIPS workshop on Tackling Climate Change with Machine Learning, 2021.
Scaling End-to-End Models for Large-Scale Multilingual ASR
Bo Li, Ruoming Pang, Tara N. Sainath, Anmol Gulati, Yu Zhang, James Qin, Parisa Haghani, W. Ronny Huang, Min Ma, Junwen Bai
IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2021.
Contrastively Disentangled Sequential Variational Autoencoder
Junwen Bai, Weiran Wang, Carla Gomes
Advances In Neural Information Processing Systems (NeurIPS), 2021.
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
Junwen Bai, Weiran Wang, Yingbo Zhou, Caiming Xiong
International Conference on Learning Representations (ICLR), 2021.
Wenting Zhao, Shufeng Kong, Junwen Bai, Daniel Fink, Carla Gomes
AAAI Conference on Artificial Intelligence (AAAI), 2021.
Junwen Bai, Shufeng Kong, Carla Gomes
International Joint Conference on Artificial Intelligence - Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI), 2020. (Acceptance rate: 12.6%)
Shufeng Kong, Junwen Bai, Jae Hee Lee, Di Chen, Andrew Allyn, Michell Stuart, Malin Pinsky, Kathy Mills, Carla Gomes
International Joint Conference on Artificial Intelligence - Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI), 2020. (Acceptance rate: 12.6%)
SWALP: Stochastic Weight Averaging in Low-Precision Training
Imitation Refinement For X-Ray Diffraction Signal Processing
Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery
CRYSTAL: a multi-agent AI system for automated mapping of materials' crystal structures
Phase Mapper: Accelerating Materials Discovery with AI
SPC: IJCAI '21
PC/reviewer: IJCAI '20, AAAI '21, IJCAI '21, ICML '21, NeurIPS '21 (Outstanding Reviewer), AAAI '22, SAS@AAAI '22, ICLR '22, ICASSP '22, IJCAI '22, AI4Good@IJCAI '22, ICML '22, NeurIPS '22, AAAI '23, ICLR '23, ICASSP '23, IJCAI '23, ICML '23, NeurIPS '23, ASRU '23, ICLR '24, ICASSP '24, Interspeech '24, ICML '24, NeurIPS '24, SLT '24
Journal reviewer: Journal of Chemometrics and Intelligent Laboratory Systems, Computational Materials Science, Transactions on Image Processing (TIP), Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Journal of Selected Topics in Signal Processing (JSTSP), Transactions on Machine Learning Research (TMLR), GeoInformatica, Transactions on Audio, Speech and Language Processing (TASL), IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), Neurocomputing, Knowledge-Based Systems, SN Computer Science, International Journal of Applied Earth Observation and Geoinformation (JAG), Applied Energy
Session Chair: IJCAI '20, ICML '22