Xinxi Zhang

Hello, I am Xinxi Zhang, a PhD student in the Department of Computer Science at Rutgers University, advised by Prof. Vladimir Pavlovic and also fortunate to work with Prof. Dimitris Metaxas . Echoing Richard Feynman’s quote that “what I cannot create, I do not understand,” my research focuses on generative modeling in computer vision, with a current emphasis on advancing efficient and robust one-step diffusion/flow-based modeling. More recently, I have been exploring representation alignment between models in two directions: using aligned representations to enhance generative modeling, and designing generative frameworks that operate across representation spaces to bridge modalities, such as vision and language.

Flow Straighter and Faster: Efficient One-Step Generative Modeling via Meanflow on Rectified Trajectories

Xinxi Zhang*, Shiwei Tan*, Quang Nguyen, Quan Dao, Ligong Han, Xiaoxiao He, Tunyu Zhang, Alen Mrdovic, Dimitris Metaxas

Re-MeanFlow enables efficient one-step generative modeling by learning mean velocities along rectified trajectories. By organically combining MeanFlow with trajectory rectification, it yields complementary strengths that neither component achieves alone. We demonstrate its generality and effectiveness on ImageNet under various settings, where Re-MeanFlow consistently outperforms previous one-step flow-based methods.

Paper (Preprint) Code ONE-STEP GENERATION EFFICIENT TRAINING

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models

Xinxi Zhang*, Song Wen*, Ligong Han*, Felix Juefei-Xu, Akash Srivastava, Junzhou Huang, Hao Wang, Molei Tao, Vladimir Pavlovic, Dimitris Metaxas

SODA is a spectrum-aware, parameter-efficient fine-tuning framework for diffusion models. We demonstrate its effectiveness on the task of personalizing text-to-image diffusion models: given only a few images of an object, SODA can generate novel scenes of the object controlled by text prompts, using only a lightweight fine-tuning stage.

PAPER (WACV 2025) DIFFUSION PERSONALIZATION PARAMETER-EFFICIENT FINE-TUNING