THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (Findings of ACL, 2022)
Corrupted Image Modeling for Self-Supervised Visual Pre-Training (ICLR, 2023)
VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts (NeurIPS, 2022)
BEiT: BERT Pre-Training of Image Transformers (ICLR, 2022) Oral paper
Attention Temperature Matters in Abstractive Summarization Distillation (ACL, 2022)
s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning (Preprint)
Learning to Sample Replacements for ELECTRA Pre-Training (Findings of ACL, 2021)
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers (Findings of ACL, 2021)
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers (NeurIPS, 2020)
Unilmv2: Pseudo-masked language models for unified language model pre-training (ICML, 2020)
Research Experience
Research Intern in Natural Language Computing at Microsoft Research Asia, Jul. 2016 – Sep. 2017, Mentor: Dr. Furu Wei; Mar. 2018 – Present, Mentors: Dr. Furu Wei & Dr. Li Dong.
Education
B.S. in School of Computer Science and Technology, Harbin Institute of Technology, Sept. 2013 - Jul. 2017; Ph.D. student in School of Computer Science and Technology, Harbin Institute of Technology, Sept. 2017 - 2023, Joint Ph.D. program with Microsoft Research Asia.
Background
Research Interests: Pre-trained models, natural language processing, representation learning. Currently a final year Ph.D. student at the School of Computer Science and Technology, Harbin Institute of Technology, advised by Prof. Songhao Piao. Also a long-term research intern at Microsoft Research Asia, mentored by Dr. Furu Wei and Dr. Li Dong.
Miscellany
No information about personal interests or hobbies is provided on the personal homepage.