Wenlong Deng

personal_img.jpg

Open to Collaboration and Internship

My name is Deng Wenlong (邓文龙), I am a Ph.D. student in the Electrical and Computer Engineering department at the University of British Columbia, co-supervised by Prof. Xiaoxiao Li and Prof. Christos Thrampoulidis. I am broadly interested in machine learning and its application in healthcare. I have conducted research on LLM efficiency, deep learning-based medical image analysis and now I am working on improving model reasoning abilities on medical diagnosis and math solving.

Previously: I obtained my master’s degree in Electrical Engineering at EPFL in 2019, where I was fortunated been supervised by Prof. Alexandre Alahi on stereo vision. I received my bachelor’s degree in Electronic and Information Engineering (Honors) at UESTC in 2017.

news

Jun 03, 2025 Check out our latest findings in On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization, where we delve into the learning dynamics of GRPO and conduct an in-depth analysis of negative gradients.
Jun 02, 2025 Delighted to share that I will be interning as a Research Scientist at Meta this summer.
Apr 01, 2025 Our paper MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs is online! We use Knowledge Graph（KG）as structured knowledge source to provide fact guidence on medical reasoning data generation.
Feb 07, 2025 Our work DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models is selected as Spotlight at ICLR, you can drop more than 99% of your delta parameters without hurt finetuned model performance! Code will be released soon.

selected publications

  1. Reasoning
    On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
    Wenlong Deng, Yi Ren , Muchen Li , and 3 more authors
    arXiv preprint arXiv:2505.18830, 2025
  2. Reasoning
    MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
    Juncheng Wu* , Wenlong Deng*, Xingxuan Li , and 12 more authors
    2025
    * Equal Contribution
    arXiv
  3. ICLR
    DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
    Wenlong Deng, Yize Zhao , Vala Vakilian , and 3 more authors
    International Conference on Learning Representations (spotlight 5%), 2025
    arXiv
  4. ICLR
    GMValuator: Similarity-based Data Valuation for Generative Models
    Jiaxi Yang* , Wenlong Deng*, Benlin Liu , and 2 more authors
    International Conference on Learning Representations, 2025
    * Equal Contribution
    arXiv
  5. cvpr_unlock.jpg
    Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
    Wenlong Deng, Christos Thrampoulidis , and Xiaoxiao Li
    The IEEE Conference on Computer Vision and Pattern Recognition, 2024
    arXiv
  6. Medical
    LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening
    Beidi Zhao , Wenlong Deng, Zi Han , and 5 more authors
    Medical Image Analysis , 2024
    arXiv
  7. Medical
    On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representations
    Wenlong Deng, Yuan Zhong , Qi Dou , and 1 more author
    In Information Processing in Medical Imaging (Accept rate 25%) , 2023
    arXiv