I’m currently focused on advancing Multimodal Large Language Models (LLMs) as a researcher with the Seed (LLM) Team at ByteDance in Singapore.

Previously, I was with Huawei Noah’s Ark Lab, also in Singapore. My academic background includes a joint PhD between the Alibaba DAMO Academy and the Singapore University of Technology and Design (SUTD), a Master of Engineering from the Massachusetts Institute of Technology (MIT), and a Bachelor of Engineering from SUTD, where I graduated with top honors.

My core research area is Natural Language Processing (NLP), with publications in top venues like ACL, EMNLP, NAACL, and AAAI. I also explore areas such as Computer Vision and Speech Recognition.

If you’re interested in a research internship or full-time role with our team, feel free to reach out!

Academic Services

Program Committee/Reviewers: ACL Acea Chair, Standing reviewer of Computational Linguistics (CL), COLM 2025, NeurIPS 2025, COLM 2024, ACL Rolling Review 2021-Present, EMNLP 2023, CL 2023, NeurIPS 2023, AAAI 2023, NeurIPS 2022, EMNLP 2022, ICML 2022, AAAI 2022, ICML 2021, ACL 2021, EMNLP 2021, NAACL 2021, AAAI 2021, ACL 2020, EMNLP 2020

Publications

• Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent
  Shanbo Cheng, Zhichao Huang, Tom Ko, Hang Li, Ningxin Peng, Lu Xu, Qini Zhang
  Technical Report, 2024

• PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
  Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song
  In Proceedings of ACL, 2024

• Parameter-Efficient Conversational Recommender System as a Language Processing Task
  Mathieu Ravaut, Hao Zhang, Lu Xu, Aixin Sun, Yong Liu
  In Proceedings of EACL, 2024

• Decomposed Prompt Tuning via Low-Rank Reparameterization
  Yao Xiao, Lu Xu, Jiaxi Li, Wei Lu, Xiaoli Li
  In Findings of EMNLP, 2023

• Sampling Better Negatives for Distantly Supervised Named Entity Recognition
  Lu Xu, Lidong Bing, Wei Lu
  In Findings of ACL, 2023

• Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
  Qingyu Tan, Lu Xu, Lidong Bing, Hwee Tou Ng
  In Findings of ACL, 2023

• Revisiting DocRED–Addressing the False Negative Problem in Relation Extraction
  Qingyu Tan*, Lu Xu*, Lidong Bing, Hwee Tou Ng, Sharifah Mahani Aljunied
  In Proceedings of EMNLP, 2022

• Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction
  Lu Xu*, Yew Ken Chia*, and Lidong Bing
  In Proceedings of ACL, 2021

• Better Feature Integration for Named Entity Recognition
  Lu Xu, Zhanming Jie, Wei Lu, and Lidong Bing
  In Proceedings of NAACL, 2021

• Position-Aware Tagging for Aspect Sentiment Triplet Extraction
  Lu Xu*, Hao Li*, Wei Lu, and Lidong Bing
  In Proceedings of EMNLP, 2020

• Aspect Sentiment Classification with Aspect-Specific Opinion Spans
  Lu Xu, Lidong Bing, Wei Lu, and Fei Huang
  In Proceedings of EMNLP, 2020

• Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis
  Haiyun Peng, Lu Xu, Lidong Bing, Fei Huang, Wei Lu, and Luo Si
  In Proceedings of AAAI, 2020