Jiahang Xu

Research SDE at Microsoft Research Asia

prof_pic.jpg

I am a Research Software Development Engineer at Microsoft Research Asia, focusing on enhancing large language model (LLM) reasoning capabilities. My current work includes test-time scaling method (rStar), along with ongoing efforts in training-based methods and reinforcement learning from human feedback (RLHF).

Previously, my research centered on efficient and scalable AI systems for hardware-aware neural architectures. I worked on neural architecture search (NAS) with projects like ElasticViT, SpaceEvo, and LitePred, as well as structured pruning techniques such as Compresso.

Before transitioning to AI systems, my early research during my M.S. at Fudan University focused on medical imaging. I developed foundational frameworks for segmentation, registration, and neurological disease analysis, contributing to early diagnosis of Alzheimer’s and Parkinson’s disease.

selected publications

  1. Preprint
    Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
    Yuanye Liu*, Jiahang Xu*, Li Lyna Zhang, and 6 more authors
    arXiv preprint arXiv:2502.04295, 2025
  2. ICLR 2025
    Mutual reasoning makes smaller llms stronger problem-solvers
    Zhenting Qi*, Mingyuan Ma*, Jiahang Xu*, and 3 more authors
    arXiv preprint arXiv:2408.06195, 2024
  3. Preprint
    Phi-3 technical report: A highly capable language model locally on your phone
    Marah Abdin, Jyoti Aneja, Hany Awadalla, and 8 more authors
    arXiv preprint arXiv:2404.14219, 2024
  4. IEEE Vis 2024
    (Best Paper Award!) VisEval: A benchmark for data visualization in the era of large language models
    Nan Chen, Yuge Zhang, Jiahang Xu, and 2 more authors
    IEEE Transactions on Visualization and Computer Graphics, 2024
  5. ICCV 2023
    Spaceevo: Hardware-friendly search space design for efficient int8 inference
    Xudong Wang, Li Lyna Zhang, Jiahang Xu, and 6 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
  6. SigKDD 2023
    Constraint-aware and ranking-distilled token pruning for efficient transformer inference
    Junyan Li, Li Lyna Zhang, Jiahang Xu, and 8 more authors
    In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
  7. Preprint
    Compresso: Structured pruning with collaborative prompting learns compact large language models
    Song Guo*, Jiahang Xu*, Li Lyna Zhang, and 1 more author
    arXiv preprint arXiv:2310.05015, 2023
  8. MedIA 2022
    Cardiac segmentation on late gadolinium enhancement MRI: a benchmark study from multi-sequence cardiac MR segmentation challenge
    Xiahai Zhuang*, Jiahang Xu*, Xinzhe Luo, and 8 more authors
    Medical Image Analysis, 2022
  9. Front. Neurosci.
    Computer-Aided Classification Framework of Parkinsonian Disorders Using 11C-CFT PET Imaging
    Jiahang Xu*, Qian Xu*, Shihong Liu*, and 8 more authors
    Frontiers in aging neuroscience, 2022
  10. Front. Neurosci.
    A fully automatic framework for parkinson’s disease diagnosis by multi-modality images
    Jiahang Xu, Fangyang Jiao, Yechong Huang, and 7 more authors
    Frontiers in neuroscience, 2019
  11. Front. Neurosci.
    Diagnosis of Alzheimer’s disease via multi-modality 3D convolutional neural network
    Yechong Huang, Jiahang Xu, Yuncheng Zhou, and 3 more authors
    Frontiers in neuroscience, 2019