Ph.D. Student

  University of Toronto

  Email: ziyiwu [at] cs.toronto.edu

I am a fifth-year PhD student in the Toronto Intelligent Systems Lab (TISL) at the University of Toronto and affiliated with the Vector Institute. My advisor is Prof. Igor Gilitschenski. I am currently a Student Researcher at Google DeepMind working with Saurabh Saxena, Marcus Brubaker, and Daniel Watson. I was a research intern at Snap research working with Aliaksandr Siarohin and Sergey Tulyakov from June 2024 to May 2025. I was a Student Researcher at Google DeepMind working with Thomas Kipf in Spring 2024.

Prior to my Ph.D., I received my Bachelor's degree from the Department of Automation, Tsinghua University, where I worked with Prof. Jiwen Lu. I did a remote summer internship in 2020 at Stanford University, advised by Prof. Leonidas J. Guibas.

I am broadly interested in designing machine learning systems that can perceive the world as we humans do, which I believe is the cornerstone of achieving AGI. Recently, I am working on controllable generative models for building powerful world models.

I will graduate next year and I am looking for industry positions on generative models starting in 2026.

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
Ziyi Wu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Ashkan Mirzaei,
Igor Gilitschenski*, Sergey Tulyakov*, Aliaksandr Siarohin*
NeurIPS 2025.
Spotlight Presentation
[Project Page]

Mind the Time: Temporally-Controlled Multi-Event Video Generation
Ziyi Wu, Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov,
Yuwei Fang, Varnith Chordia, Igor Gilitschenski*, Sergey Tulyakov*
CVPR 2025.
[Project Page]  [Slides]

SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation
Koichi Namekata, Sherwin Bahmani, Ziyi Wu, Yash Kant,
Igor Gilitschenski, David B. Lindell
ICLR 2025.
[Project Page (with paper and code)]

Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
Ziyi Wu, Yulia Rubanova, Rishabh Kabra, Drew A. Hudson, Igor Gilitschenski,
Yusuf Aytar, Sjoerd van Steenkiste, Kelsey Allen, Thomas Kipf
NeurIPS 2024.
Spotlight Presentation
[Project Page (with paper and code)]  [Slides]

SPAD: Spatially Aware Multiview Diffusers
Yash Kant, Ziyi Wu, Michael Vasilkovsky, Guocheng Qian, Jian Ren, Riza Alp Guler,
Bernard Ghanem, Sergey Tulyakov*, Igor Gilitschenski*, Aliaksandr Siarohin*
CVPR 2024.
[Project Page (with paper, code, and slides)]

SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Ziyi Wu, Jingyu Hu*, Wuyue Lu*, Igor Gilitschenski, Animesh Garg
NeurIPS 2023 | ICLR@NeSy-GeMs workshop, 2023.
Spotlight Presentation
[Project Page (with paper and code)]  [Slides]

SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
Ziyi Wu, Nikita Dvornik, Klaus Greff, Thomas Kipf*, Animesh Garg*
ICLR 2023 | UAI@CRL workshop, 2022 | ECCV@MVCS Challenge, 2022.
[Project Page (with paper and code)]  [Slides]

TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
Mohammad Mohammadi, Ziyi Wu, Igor Gilitschenski
ICCV 2025.
[Paper]  [Code]

LEOD: Label-Efficient Object Detection for Event Cameras
Ziyi Wu, Mathias Gehrig, Qing Lyu, Xudong Liu, Igor Gilitschenski
CVPR 2024.
[Paper]  [Code]  [Slides]

Breaking Bad: A Dataset for Geometric Fracture and Reassembly
Silvia Sellán*, Yun-Chun Chen*, Ziyi Wu*, Animesh Garg, Alec Jacobson
NeurIPS 2022 Datasets and Benchmarks Track.
Featured Paper Presentation
[Project Page (with paper, code, and data)]  [Slides]

Instance Similarity Learning for Unsupervised Feature Representation
Ziwei Wang, Yunsong Wang, Ziyi Wu, Jiwen Lu, Jie Zhou
ICCV 2021.
[Paper]  [Code]

Learning Efficient Binarized Object Detectors with Information Compression
Ziwei Wang, Jiwen Lu, Ziyi Wu, Jie Zhou
T-PAMI 2021.
[Paper]

BiDet: An Efficient Binarized Object Detector
Ziwei Wang, Ziyi Wu, Jiwen Lu, Jie Zhou
CVPR 2020.
[Paper]  [Code]  [Slides]

Journal reviewer: T-PAMI; TMLR; ISRR; RA-L;
Conference reviewer: CVPR'22-25; ICCV'23-25; ECCV'22-24; NeurIPS'22-25; ICML'23-25; ICLR'24-25; AAAI'23-24; IJCAI'24; IROS'22; ICRA'23-24;
Workshop reviewer: OSC@ICLR'22; CVEU@CVPR'25;

Teaching Assistant, CSC 478: Robotics Perception23 Winter
Teaching Assistant, CSC 108: Introduction to Computer Programming21 Fall, 22 Winter, 22 Fall, 23 Summer

I like basketball and soccer. My favorite players are LeBron James (well, associate G.O.A.T.?) and Lionel Messi (real G.O.A.T.!).

I love reading (especially when I am stuck in research). My main interests are ethics, human nature and values. My favorite books are One Hundred Years of Solitude, 1984, The Plague, The World of Yesterday (added, 2024.1, a great book for this era, where the old regime is being destroyed), and Dream of the Red Chamber (红楼梦). Some of my recent (since 2021) reading are Ernest Hemingway (what makes the transition from For Whom the Bell Tolls to The Old Man and the Sea?), Michel Foucault ("modern society is like a Panopticon"), Hannah Arendt (the modernity of holocaust), Milan Kundera (Immortality), Mo Yan (莫言) (《蛙》), Tocqueville (The Old Regime is here, where is the ___?),

I am also an Anime fan and a lover of Visual Novel and JRPG. Some of my favorite works are EVA, Fate/Stay Night, Perfect Blue, FLCL, Madoka Magica, Steins;Gate, Hyouka, Bocchi the Rock, Subarashiki Hibi (a.k.a. Wonderful Everyday), and Persona 5.

Two persons I admire the most: Kaiming He for his outstanding research tastes ("All great truths are simple in final analysis") and Elon Musk for his aspiration and enthusiasm (now in doubt, 2022.12. "Power tends to corrupt and absolute power corrupts absolutely") (2025.2, blocked this guy on Twitter, why did I ever admire him before...).

I write an article (in Chinese) summarizing the experience during my CS PhD application process. Take a look here!