Zhan Zhuang is a Ph.D. Candidate in Computer Science at CityUHK, specializing in post-training and transfer learning for foundation models, with an expected graduation in June 2026. He boasts an extensive publication record in top-tier AI/ML venues including ICLR, ICML, NeurIPS, and ICCV, complemented by industry experience from ByteDance. His expertise in parameter-efficient updates, automated self-improvement, and long-context memory mechanisms positions him to develop robust, generalizable, and self-improving AI systems.
Research Intern
Shenzhen, Guangdong, China
→
Summary
Conducted hands-on industry research at ByteDance Seed Research, contributing to advanced projects in foundation models and self-improving learning systems.
Highlights
Developed and implemented parameter-efficient update strategies for foundation models, enabling frequent, low-cost model refreshes while preserving prior capabilities.
Contributed to the design and evaluation of automated self-improvement mechanisms, utilizing curriculum/data synthesis and self-evaluation for robust model performance.
Explored and integrated long-context and memory architectures, significantly improving task completion and generalization for complex AI systems.
Applied hands-on industry experience to optimize large-scale AI systems, ensuring deployment feedback loops for continuous improvement and robust generalization.
→
Ph.D.
Computer Science
→
B.Eng.
Computer Science and Technology
Awarded By
CityUHK
Recognized for exceptional academic achievement and contributions during Ph.D. studies.
Awarded By
SUSTech
Awarded for distinguished academic performance and overall contributions as a graduating student.
Awarded By
SUSTech
Acknowledged as one of the top 10 graduates from Shude College, demonstrating academic excellence.
Awarded By
SUSTech
Recognized for outstanding leadership and service in student organizations.
Awarded By
SUSTech
Awarded for exemplary commitment and active participation within the student league.
Published by
Granted Patent (CN112866991B)
Summary
Invented and patented a method and device for acquiring close contact information, enhancing public health initiatives.
Published by
Granted Patent (CN112635061B)
Summary
Developed and patented a novel data processing method and device leveraging blockchain technology for secure and efficient information management.
Published by
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Summary
Authored research on heterogeneity-aware distillation, advancing lifelong heterogeneous learning in computer vision.
Published by
Thirteenth International Conference on Learning Representations (ICLR)
Summary
Co-authored work on mosaic shared adaptation, improving parameter-efficient fine-tuning for large language models.
Published by
International Conference on Computer Vision (ICCV)
Summary
Introduced PLAN, a proactive low-rank allocation strategy to optimize continual learning performance.
Published by
Thirteenth International Conference on Learning Representations (ICLR)
Summary
Presented HiRA, an oral presentation (top 1.8%) on parameter-efficient Hadamard high-rank adaptation for LLMs, enhancing model efficiency.
Published by
Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI)
Summary
Delivered an oral presentation on Moonshine, a method for distilling game content generators into steerable generative models.
Published by
Forty-Second International Conference on Machine Learning (ICML)
Summary
Proposed a progressive strategy to significantly boost low-rank adaptation in machine learning models.
Published by
Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS)
Summary
Developed MoPFormer, a novel transformer architecture for enhancing wearable-sensor activity recognition.
Published by
Twelfth International Conference on Learning Representations (ICLR)
Summary
Published research on gradual domain adaptation using gradient flow, recognized as a Spotlight paper (top 5%) for its innovative approach.
Published by
IEEE Conference on Games
Summary
Awarded 'Best Paper' (top 5%) for extending the Wave Function Collapse algorithm to enable large-scale content generation.
Python, Java, C, C#, JavaScript, SQL, Scala, Verilog, HTML5.
Linux, Android, Unity, Arduino, Web Development, STM32, Jetson Nano, Hololens.
Foundation Models, Transfer Learning, Continual Learning, Parameter-Efficient Fine-Tuning (PEFT), Large Language Models (LLM), Computer Vision (CV), Neural Information Processing Systems, Deep Learning, Generative Models, Reinforcement Learning.
Algorithmic Screening, Data Synthesis, Self-Evaluation, High-Performance Computing (HPC), Model Optimization, Deployment Feedback Loops, Strategic Prioritization.