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

Dec 30, 2025 Delighted to share that I will be interning as a Applied Scientist at Amazon Annapurna Labs starting mid-January, where I’ll be working on multi-turn reinforcement learning.
Dec 03, 2025 Our paper On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral is online! We investigate why GRPO fails within Search-R1 (a recent multi-turn agentic workflow powered by DeepSeek-R1), showing that LLD is also the root cause of GRPO failure in multi-turn, tool-integrated RL.
Sep 18, 2025 Out paper On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization is accepted by NeurIPS 2025, where we delve into the learning dynamics of GRPO and conduct an in-depth analysis of negative gradients.
Jul 10, 2025 Our work Token Hidden Reward: Steering Exploration-Exploitation in GRPO Training has been selected as a Best Paper at the 2nd AI for Math Workshop @ ICML 2025. In this paper, we investigate how to guide the balance between exploitation and exploration in RL training using a free-launch token-level reward.

selected publications

  1. Agent Reasoning
    On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral
    Wenlong Deng, Yushu Li , Boying Gong , and 3 more authors
    arXiv preprint arXiv:2512.04220, 2025
  2. Reasoning
    On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
    Wenlong Deng, Yi Ren , Muchen Li , and 3 more authors
    NeurIPS, 2025
  3. 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
  4. Efficiency
    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
  5. Data Value
    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
  6. 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
  7. 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
  8. 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