I am a second-year Master’s student in Data Science at Tsinghua University, advised by Prof. Shao-Lun Huang. Before that, I earned my B.S. in Electronic Engineering from Sun Yat-sen University (SYSU) in 2022, under the guidance of Prof. Yulan Guo. Currently I’m a research intern at Microsoft Research Asia, working with Dr. Yeyun Gong. I also interned at Tencent AI Lab, collaborating with Dr. Pengyu Cheng.

My current research focuses on pre-training strategy and reinforcement learning (RL) for Large Language Models (LLMs), with a long-term aim at AGI. I am excited to apply for Fall 2025 PhD programs and investigate potential collaborations. If you are interested in discussing opportunities or have any questions, please feel free to EMAIL me. I genuinely appreciate your consideration and look forward to connecting with you.

📖Education

• Aug. 2022 - Jun. 2025 (Expected) M.Sc., Data Science and Information Technology, Tsinghua University, Beijing, China.
  GPA: 3.98/4.0, Top 3%

• Sep. 2018 - Jun. 2022 B.Sc., Electronic Information Science and Technology, Sun Yat-sen University, Guangzhou, China.
  GPA: 4.11/5.0, Top 3%

📑Publications

	Task Oriented In-Domain Data Augmentation Xiao Liang* , Xinyu Hu*, Simiao Zuo, Yeyun Gong, Qiang Lou, Yi Liu, Shao-Lun Huang, Jian Jiao Preprint 2024, [PDF] We propose a task-oriented in-domain data augmentation framework consisting of in-domain data selection and task-oriented synthetic passage generation.
	Exploring Iterative Refinement with Diffusion Models for Video Grounding Xiao Liang*, Tao Shi*, Yaoyuan Liang, Te Tao, Shao-Lun Huang ICME 2024, [PDF] [Code] We propose a novel framework with diffusion models that formulates video grounding as a conditioned generation task, enhancing predictions through iterative refinement.
	CoSTA: End-to-End Comprehensive Space-Time Entanglement for Spatio-Temporal Video Grounding Yaoyuan Liang*, Xiao Liang* , Yansong Tang, Zhao Yang, Ziran Li, Jingang Wang, Wenbo Ding, Shao-Lun Huang AAAI 2024, [PDF] We propose a framework of Comprehensive Space-Time entAnglement to densely entangle space-time multi-modal features for spatio-temporal localization.
	SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations Tao Shi*, Xiao Liang* , Yaoyuan Liang, Xinyi Tong, Shao-Lun Huang Preprint 2023, [PDF] [Code] We introduce utilizing label representations by projecting discrete labels into dense embeddings for multimodal emotion classification.
	Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers Jiawen Xie, Pengyu Cheng, Xiao Liang , Yong Dai, Nan Du ACL 2024, [PDF] [Code] We propose a token selection framework for pre-trained transformers to process long sequences utilizing reinforcement learning.

(* indicates equal contribution)

🧑‍💻Experience

• (Nov. 2023 - Present) Reserch Intern, NLC Group, Microsoft Research Asia, Beijing, China.
  Mentor: Yeyun Gong
  Working on large language models, pre-training strategy and model architecture.

• (Mar. 2023 - Sep. 2023) Research Intern, AI Lab, Tencent Inc., Guangdong, China.
  Mentor: Pengyu Cheng, Nan Du
  Working on large language models, long sequence processing.

🏆Honors and Awards

• Outstanding Graduate Thesis, Sun Yat-sen University, Guangdong, 2022
• Outstanding Graduate Student, Sun Yat-sen University, Guangdong, 2022
• Second Prize Scholarship, Sun Yat-sen University, Guangdong, 2019~2022
• 1st of the 2022 Tsinghua Open Hack Competition - Multimodal Learning Track, Tsinghua University, Beijing, 2022