Scholar
Tianyu Liu
Google Scholar ID: 6hHbBwwAAAAJ
Alibaba
Citations & Impact
Citations
17,541
H-index
38
i10-index
62
Publications
20
Co-authors
24
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published multiple papers including 'Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding', 'Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond', 'Making Large Language Models Better Reasoners with Alignment', and more. Additionally, released the FairEval platform for LLM comparisons.
Research Experience
- Currently a researcher at Alibaba’s Qwen Team, previously a senior researcher at Tencent Cloud AI. His research experiences cover natural language generation, information extraction, and robustness of NLP models. Since 2021, his research interests have shifted to the pretraining and alignment of large language models.
Education
- Earned his PhD degree from Peking University in 2021, advised by Zhifang Sui and Baobao Chang. During his PhD, he interned or visited Microsoft Research (Beijing and Redmond) and Toyota Technological Institute at Chicago (TTIC).
Background
- Currently a researcher at Alibaba’s Qwen Team, focusing on the pretraining and alignment of large language models. Previously, he was a senior researcher at Tencent Cloud AI, contributing to the development of HuyuanAide (Tencent’s proprietary LLM series). His research interests include natural language generation, information extraction, and robustness of NLP models.
