Zhewei Fang

About Me

I am currently a master’s student in Computer Science and Technology at Hangzhou Dianzi University, advised by Prof. Zhou Yu. I received my bachelor’s degree from Taizhou University, where I was advised by Prof. Shiqing Zhang.

I am currently a research intern with the MNN team at Taobao, Alibaba Group, working on on-device language models, post-training, and multimodal learning.

I have received the National Scholarship, the Outstanding Graduate of Zhejiang Province award, and an Outstanding Graduation Thesis award.

Research Interests

My research focuses on large language model post-training, unified multimodal models, agentic reinforcement learning, and multimodal understanding and generation.

My other research interests include pattern recognition, image quality assessment, and multimodal affect recognition.

Experience

Alibaba Group (Taobao) · Meta Team

Algorithm Research Intern · 2025–2026

  • Contributed extensively to the MNN-Pocket post-training pipeline, including data, SFT, RL, MOPD, quantization, evaluation, and on-device deployment.
  • Built an SFT Loop Engine with failure analysis, synthetic data generation, and iterative training, improving average performance across 11 tasks by 7.46 percentage points.
  • Contributed to multi-teacher distillation and QAT, compressing a 302.8M-parameter model to 166 MB. MNN open-source models accumulated over 6K downloads.
  • Led Imp-o 1B–3B training and Sana-Turbo on-device acceleration, and advanced device–cloud agentic RL experiments.

Open Source

Total Downloads —
Primary Developer

MNN-Pocket

On-device Small Models · Post-training & Deployment

As a primary developer, contributed extensively to data construction, SFT, RL, multi-teacher distillation, quantization, and evaluation to bring models to on-device deployment with MNN.

Series Downloads · Last 30 Days
—
Series Downloads · All Time
—

Total download counts across all MNN-Pocket model repositories published by taobao-mnn.

Loading download statistics…

Primary Developer

MNN-Sana-Edit-V2

taobao-mnn · Hugging Face

Led the on-device development and optimization of MNN-Sana-Edit-V2, including model adaptation, inference acceleration, and open-source delivery with MNN.

Downloads · Last 30 Days
—
Downloads · All Time
—

Loading download statistics…

Publications

IEEE TPAMI · AcceptedSole First Author

PerDepNet: Personality-guided Cross-domain Multitask Learning Network for Automated Video Depression Detection

Zhewei Fang, Kaiyin Lian, Shiqing Zhang, Zhou Yu, Jun Yu, Siwei Ma, Qi Tian

Introduces personality-domain information with cross-domain multitask learning and audiovisual fusion to better model depression-related emotional cues.

Personality information guides depression prediction through shared video representations
Concept Illustration
PREPRINT · 2026Co-first Author

Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks

Zhewei Fang, Yuxin Zhang, Zhenwei Shao, Mengze Li, Zheng Lin, Long Chen, Zhou Yu, Zhe Chen, Zhiwen Chen, Zhaode Wang, Chengfei Lv

Trains on-device small models to learn when to consult cloud models and internalize their guidance. Self-evolving RL, consultation cold start, and consultation-aware RL improve long-horizon task success while reducing cloud calls.

Sibyl selectively consults a cloud model during on-device task execution
Collaboration Overview · Figure 1
IEEE TIM · PublishedFirst Author

Blind 3D-synthesized Image Quality Measurement by Analysis of Local and Global Statistical Properties

Zhewei Fang, Yueli Cui, Mei Yu, Gangyi Jiang, Kaiyin Lian, Yulu Wen, Jiayao Xu

Combines local and global statistical features to characterize virtual-view synthesis distortions and predict image quality without a reference image.

Local and global statistics are fused for no-reference image quality prediction
Concept Illustration

Honors & Awards

  • National Scholarship (2023)
  • Huawei ICT Competition · Global Second Prize / National First Prize (2023)
  • CCF YOCSEF Academic Showcase · National Second Prize (2024)
  • China International “Internet+” College Students Innovation and Entrepreneurship Competition · National Silver Award (2024)