Ziteng Gao

I am a last-year PhD student at the National University of Singapore (NUS), currently working at the Show Lab under the supervision of Prof. Mike Z. Shou.

I play with generative vision, especially with pixels.

Previously, I received my M.Sc. degree from Nanjing University in 2022, advised by Prof. Limin Wang. I obtained my B.Sc. degree from the same institution in 2019 as a member of the Computer Science Elite Class.

gzt [at] outlook.com

[github] [google scholar]

I am always seeking full-time research or engineering positions in industry starting late 2026. Feel free to reach out via the email above if you think I would be a good fit for your team.

avatar

Selected Papers & Preprints, Full List

D-AR: Diffusion via Autoregressive Models

Ziteng Gao, Mike Zheng Shou

TL;DR: Simulating pixel diffusion process with autoregressive models via next token prediction.

ICLR, 2026

[arxiv] [code]


PixNerd: Pixel Neural Field Diffusion

Shuai Wang, Ziteng Gao, Chenhui Zhu, Weilin Huang, Limin Wang

TL;DR: The first large-patch diffusion transformers on pixels.

ICLR, 2026

[arxiv] [code]


Sparse Image Synthesis via Joint Latent and RoI Flow

Ziteng Gao, Jay Zhangjie Wu, Mike Zheng Shou

NeurIPS, 2025 [new]

[paper & code to be released]

Bootstrapping SparseFormers from Vision Foundation Models

Ziteng Gao, Zhan Tong, Kevin Qinghong Lin, Joya Chen, Mike Zheng Shou

CVPR, 2024

[arxiv] [pdf] [code]


SparseFormer: Sparse Visual Recognition via Limited Latent Tokens

Ziteng Gao, Zhan Tong, Limin Wang, Mike Zheng Shou

ICLR, 2024

[arxiv] [pdf] [code]


AdaMixer: A Fast-Converging Query-Based Object Detector

Ziteng Gao, Limin Wang, Bing Han, Sheng Guo

CVPR, 2022 (oral)

[arxiv] [pdf] [code] [slides]


Mutual Supervision for Dense Object Detection

Ziteng Gao, Limin Wang, Gangshan Wu

ICCV, 2021

[arxiv] [pdf]


Boundary-Aware Cascade Networks for Temporal Action Segmentation

Zhenzhi Wang, Ziteng Gao, Limin Wang, Zhifeng Li, Gangshan Wu

ECCV, 2020

[pdf] [code]


LIP: Local Importance-based Pooling

Ziteng Gao, Limin Wang, Gangshan Wu

ICCV, 2019

[arxiv] [pdf] [code]