Yifan Wang

Phd Student · Smile Lab @ Northeastern University

About

I am a PhD candidate at SMILE Lab @ Northeastern University, supervised by Prof. Yun Raymond Fu . Before that, I obtained my Bachelor's degree in Mathematics and applied mathematics from Shandong university, Jinan, Shandong, China. Currently, I'm also a research intern at Snap Inc. where I'm working closely with Yanyu Li, Anil Kag, Gorden Qian and Sergey Tulyakov, My research currently centers on the post-training of the generative models. Also, I have experience of model efficiency and MLLM agent. Feel free to contact for anything! σ`∀´)σ

News

Feb 2026 — One paper got accepted by ICLR2026!
Jun 2025 — Begin my internship at Snap.
May 2024 — One paper got accepted by IJCV!
Jan 2024 — One paper got accepted by TCDS!
Sep 2023 — Begin my Phd life at NEU

Publications & Pre-prints

Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning

Yifan Wang, Yanyu Li, Gordon Guocheng Qian, Sergey Tulyakov, Yun Fu, Anil Kag

Under review

Webpage

GmNet: Revisiting Gating Mechanisms From A Frequency View

Yifan Wang, Xu Ma, Yitian Zhang, Yizhou Wang, Zhongruo Wang, Sung-Cheol Kim, Vahid Mirjalili, Vidya Renganathan, Yun Fu

ICLR 2026 poster

PDF · Code

Exploiting inter-sample affinity for knowability-aware universal domain adaptation

Yifan Wang, Lin Zhang, Ran Song, Hongliang Li, Paul L Rosin, Wei Zhang

International Journal of Computer Vision

PDF · Code

Neighborhood-aware mutual information maximization for source-free domain adaptation

Lin Zhang, Yifan Wang, Ran Song, Mingxin Zhang, Xiaolei Li, Wei Zhang

IEEE Transactions on Multimedia

PDF

Dual-graph contrastive learning for unsupervised person reidentification

Lin Zhang, Ran Song, Yifan Wang, Qian Zhang, Wei Zhang

IEEE Transactions on Cognitive and Developmental Systems

PDF

Experience

Research Intern · Creative Vision @ Snap Inc.

May 2025 – Now · Santa Monica, CA, USA

Exploring differentiable reward finetuning for video diffusion model.

Research Assistant · Smile Lab @ NEU

2023 – Present