研究方向

深度学习，强化学习，科学智能，大语言模型。

学术专著

Tao Qin. Dual Learning, Springer 2020.

主要成就与荣誉

• 2017年以计算机科学家的身份荣获《北京青年》周刊 “年度匠人精神青年榜样” 奖项

• 提出的对偶学习助力微软在2018年中英新闻翻译任务上达到了人类专家水平；

  • 带领团队在WMT2019机器翻译大赛中获得8个项目的冠军

• 2019年设计了当时最高效的语音合成模型FastSpeech，实现了百倍的加速，并成为微软云Azure服务上支持100多种语言和200多种语音的基础模型组件。

• 2019开发了有史以来最强大的麻将AI Suphx，成为“天凤”平台上首个升至十段的AI，其稳定段位显著优于人类顶尖选手；

• 2020年在国际知名的学术出版集团施普林格·自然（Springer Nature）出版了学术专著《对偶学习》；

• 2022年发布了BioGPT模型，在生命科学领域大幅超越了其他大型语言模型，并在PubMed问答任务上首次达到了人类专家的水平。

  • 荣获ICDM 2022最佳学生论文亚军

代表性学术论文

NatureLM: Deciphering the Language of Nature for Scientific Discovery. arXiv 2025.

TamGen: drug design with target-aware molecule generation through a chemical language model. Nature Communications 2024.

HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model. arXiv 2025.

E2Former: A Linear-time Efficient and Equivariant Transformer for Scalable Molecular Modeling. arXiv 205.

Accelerating protein engineering with fitnesslandscape modeling and reinforcement learning. bioRxiv 2023.

BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in Bioinformatics 2022

The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4. arXiv 2023.

FABind: Fast and Accurate Protein-Ligand Binding. NeurIPS 2023.

SMT-DTA: Improving Drug-Target Affinity Prediction with Semi-supervised Multi-task Training. Briefings in Bioinformatics 2023.

Pre-training Antibody Language Models for Antigen-Specific Computational Antibody Design. KDD 2023.

Dual-view Molecular Pre-training. KDD 2023.

Retrosynthetic Planning with Dual Value Networks. ICML 2023.

De Novo Molecular Generation via Connection-aware Motif Mining. ICLR 2023.

O-GNN: incorporating ring priors into molecular modeling. ICLR 2023.

R2-DDI: Relation-aware Feature Refinement for Drug-Drug Interaction Prediction. Briefings in Bioinformatics 2022.

Direct Molecular Conformation Generation. TMLR 2022.

Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models. arXiv preprint 2023

Learning to rank: from pairwise approach to listwise approach. International Conference on Machine Learning (ICML) 2007

Fastspeech 2: Fast and high-quality end-to-end text to speech. International Conference on Learning Representations (ICLR) 2021

MPnet: Masked and permuted pre-training for language understanding. NeurIPS 2020

Fastspeech: Fast. robust and controllable text to speech. NeurIPS 2019

Generalizing to unseen domains: A survey on domain generalization. IEEE Transactions on Knowledge and Data Engineering (TKDE) 2022

Mass: Masked sequence to sequence pre-training for language generation. International Conference on Machine Learning (ICML) 2019

Dual learning for machine translation. NeurIPS 2016

Neural architecture optimization. NeurIPS 2018

Achieving human parity on automatic Chinese to English news translation. arXiv preprint 2018

LETOR: A benchmark collection for research on learning to rank for information retrieval. Information Retrieval Journal 2010

R-drop: Regularized dropout for neural networks. NeurIPS 2021

Incorporating BERT into neural machine translation. ICLR 2020

A survey on neural speech synthesis. arXiv preprint 2021

Introducing LETOR 4.0 datasets. arXiv preprint 2013

Can generalist foundation models outcompete special-purpose tuning? Case study in medicine. arXiv preprint 2023

An empirical study on learning to rank of tweets. ACM SIGIR 2008

Image-to-image translation: Methods and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2020

Feature selection for ranking. European Conference on Machine Learning (ECML) 2003

Representation degeneration problem in training natural language generation models. ACL 2020

Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers. NeurIPS 2023

Multilingual neural machine translation with knowledge distillation. ACL 2020

NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality. NeurIPS 2022

Frank: a ranking method with fidelity loss. ACM SIGIR 2019

Adaspeech: Adaptive text to speech for custom voice. Interspeech 2021

Deliberation networks: Sequence generation beyond one-pass decoding. ACL 2021

Understanding and improving transformer from a multi-particle dynamic system point of view. NeurIPS 2021

Learning to teach. ICML 2017

A study of reinforcement learning for neural machine translation. ACL 2016

Supervised rank aggregation. ACM SIGKDD 2012

Query dependent ranking using k-nearest neighbor. ACM SIGIR 2008

Fully parameterized quantile function for distributional reinforcement learning. ICML 2020