Xu Guo

I am a Wallenberg-NTU Presidential Postdoctoral Fellow, starting from 2023. I am currently based at KTH, Sweden, working with Mikael Skoglund. I spent the first half of my fellowship at NTU, Singapore, where I worked with Miao Chun Yan. I received my Ph.D. from NTU in 2023, advised by Han Yu.

Research Interests

My research lies at the intersection of Machine Learning and Natural Language Processing, with a focus on efficient and generative techniques for LLMs.

Efficient/Low-Resource Methods for NLP

  • Data-efficient learning for downstream tasks
  • Lightweight model adaptation and training strategies
  • Fast and cost-effective inference techniques

Generation

  • Synthetic data generation for downstream tasks
  • Data augmentation via controlled generation
  • Generating auxiliary signals to support reasoning and learning

Preprints

  • [NEW] SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning
    Yige Xu*, Xu Guo*, Zhiwei Zeng, Chunyan Miao . [Paper][Code]

Publications 📖

  • SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs.
    Yige Xu*, Xu Guo*, Zhiwei Zeng, Chunyan Miao
    ACL, 2025 [Paper][Code][Data]
  • Diffusion-Guided Diversity for Single Domain Generalization in Time Series Classification
    Junru Zhang, Lang Feng, Xu Guo, Han Yu, Yabo Dong, Duanqing Xu
    KDD, 2025
  • RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference
    Yige Xu, Xu Guo, Zhiwei Zeng, Chunyan Miao
    EMNLP, 2024 [Lecture][Paper][Code]
  • A Survey on Natural Language Counterfactual Generation
    Yongjie Wang*, Xiaoqi Qiu*, Yue Yu, Xu Guo, Zhiwei Zeng, Yuhong Feng, Zhiqi Shen.
    EMNLP Findings, 2024 [Paper]
  • Generating Synthetic Datasets for Few-shot Prompt Tuning
    Xu Guo, Zilin Du, Boyang Li, Chunyan Miao
    COLM, 2024 [Poster][Paper]
  • PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning
    Xiaoqi Qiu*, Yongjie Wang*, Xu Guo, Zhiwei Zeng, Yue Yu, Yuhong Feng, and Chunyan Miao
    ACL, 2024 [Lecture][Paper][Code]
  • InteMATs: Integrating Granularity-Specific Multilingual Adapters for Cross-Lingual Transfer
    Meizhen Liu, Xu Guo, Jiakai He, Jianye Chen, Fengyu Zhou, and Siu Hui
    EMNLP Findings, 2023 [Paper]
  • GranCATs: Cross-Lingual Enhancement through Granularity-Specific Contrastive Adapters
    Meizhen Liu, Jiakai He, Xu Guo, Jianye Chen, Siu Cheung Hui, and Fengyu Zhou
    CIKM, 2023 [Paper][Code]
  • Training Multimedia Event Extraction With Generated Images and Captions
    Zilin Du, Yunxin Li, Xu Guo, Yidan Sun, and Boyang Li
    ACM MM, 2023 [Paper][Code]
  • Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
    Xu Guo, Boyang Li, Han Yu
    EMNLP Findings, 2022 [Lecture][Paper][Code]
  • Federated learning for personalized humor recognition
    Xu Guo, Han Yu, Boyang Li, Hao Wang, Pengwei Xing, Siwei Feng, Zaiqing Nie, and Chunyan Miao
    ACM TIST, 2022 [Paper]
  • Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
    Xu Guo, Boyang Li, Han Yu, Chunyan Miao
    NAACL, 2021 [Lecture][Paper][Code]

Honors and Awards 🏆

  • Wallenberg-NTU Presidential Postdoctoral Fellowship. 2023
  • WiEST Development Grant. Women in Engineering, Science, and Technology, NTU. 2023
  • Best Presentation Award. Pattern Recognition and Machine Intelligence Association. 2021
  • Best Application Paper Award. International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with IJCAI 2020
  • Student Travel Grant. Awarded by IJCAI. 2019
  • NTU Research Scholarship. NTU, Singapore. 2019