Biography

I am a researcher at BlueImage Lab, vivo Mobile Communication Co., Ltd, working with Dr. Bo Li. I received my Ph.D. from Shanghai Jiao Tong University in 2025, advised by Prof. Jia Wang, and my B.Eng. from Xidian University in 2020. During my studies, I interned at Youtu Lab@Tencent, BlueImage Lab@vivo, Advertising Marketing Services (AMS)@Tencent, and AI Lab@Midea.
Recently, my research interests focus on Generative Models and Multimodal Large Language Models. If you are interested in chatting with me, feel free to drop me an email.

Work & Intern Experience

BlueImage Lab@vivo Work

Researcher · Jul. 2025 - Present

Advertising Marketing Services (AMS)@Tencent Intern

Intern · Mar. 2025 - Jun. 2025

BlueImage Lab@vivo Intern

Research Intern · Oct. 2023 - Mar. 2025

Youtu Lab@Tencent Intern

Research Intern · Jan. 2022 - Oct. 2023

AI Lab@Midea Intern

Research Intern · Jul. 2021 - Dec. 2021

Education

Shanghai Jiao Tong University

Ph.D. in Electronic Engineering

Sep. 2020 – Jun. 2025

School of Information Science and Electronic Engineering

Advisor: Prof. Jia Wang

Xidian University

B.Eng. in Electronic Engineering

Sep. 2016 – Jun. 2020

School of Aerospace Science and Technology

Research Interests

Generative Models MLLM Computer Vision Machine Learning

News Recent Updates

Sep 2026 · Paper Two NeurIPS 2026 papers accepted · Congratulations to Dr. Tang and Dr. Gao!

Jul 2026 · Paper TMLR 2026 paper accepted

Feb 2026 · Paper CVPR 2026 paper accepted (Highlight) · Congratulations to Dr. Gao!

Publications

(C: Conference | J: Journal | P: Preprint | *: Equal Contribution)

Conference

NeurIPS 2026

[C13] PhysRemover: A Unified Framework for Physically Realistic Object Removal

Dongxu Yue, Weixuan Jin, Yuhang Yu, Bo Li, Qi Wen, Xinrui Chen, Jinwei Chen, Tianyi Zheng, Hao Zhang, Zhihai He, Chun Yuan

[Paper] Conference on Neural Information Processing Systems (NeurIPS) 2026

NeurIPS 2026 Co-first author

[C12] Opening the Black Box of Classifier-Free Guidance via Information Bottleneck

Jiayang Gao*, Tianyi Zheng*, Jiayang Zou, Fengxiang Yang, Luyao Fan, Lv Tang, Bo Li, Jia Wang

[Paper] Conference on Neural Information Processing Systems (NeurIPS) 2026

NeurIPS 2026 Co-first author

[C11] Visual Text Compression as Measure Transport

Lv Tang*, Tianyi Zheng*, Yang Liu, Bo Li, Xingyu Li

[Paper] Conference on Neural Information Processing Systems (NeurIPS) 2026

ECCV 2026

[C10] JSON: Jigsaw Self-play Optimization for Normalizing Flows

Fengxiang Yang, Tianyi Zheng, Jinwei Chen, Bo Li

[Paper] European Conference on Computer Vision (ECCV) 2026

ECCV 2026

[C9] GR-GRPO: Graph-Diffused Credit for Autoregressive Image RL Alignment

Zheyu Zhang, Peng-Tao Jiang, Tianyi Zheng, Jian Zhang, Jinwei Chen, Bo Li

[Paper] European Conference on Computer Vision (ECCV) 2026

ICML 2026

[C8] B-Spar: Bayesian Sparse-Reward Modeling for RL-based Image Editing

Shusong Xu, Peiye Liu, Yongbin Liu, Bangjie Yin, Tianyi Zheng, Zhaomang Sun, Zhenyu Chen, Peng-Tao Jiang, Jian Zhang, Yuzhao Wang, Zhen Gu, Jinwei Chen, Bo Li

[Paper] International Conference on Machine Learning (ICML) 2026

CVPR 2026 Highlight Co-first author

[C1] C²FG: Control Classifier-Free Guidance via Score Discrepancy Analysis

Jiayang Gao*, Tianyi Zheng*, Jiayang Zou, Fengxiang Yang, Shice Liu, Luyao Fan, Zheyu Zhang, Hao Zhang, Jinwei Chen, Peng-Tao Jiang, Bo Li, Jia Wang

[Paper] IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2026 Highlight

ICLR 2026

[C2] I-DRUID: Layout to Image Generation via Instance-Disentangled Representation and Unpaired Data

Fengxiang Yang, Tianyi Zheng, Bangjie Yin, Shice Liu, Jinwei Chen, Peng-Tao Jiang, Bo Li

[Paper] International Conference on Learning Representations (ICLR) 2026

AAAI 2026 Oral First author

[C3] Bidirectional Noise Injection: Enhancing Diffusion Models via Coordinated Input-Output Perturbation

Tianyi Zheng, Jiayang Gao, Peng-Tao Jiang, Fengxiang Yang, Ben Wan, Hao Zhang, Jinwei Chen, Jia Wang, Bo Li

[Paper] AAAI Conference on Artificial Intelligence (AAAI) 2026 Oral

ICASSP 2025 Oral

[C4] Pruning for Sparse Diffusion Models based on Gradient Flow

Ben Wan, Tianyi Zheng, Zhaoyu Chen, Yuxiao Wang, Jia Wang

[Paper] IEEE ICASSP 2025 Oral

ACM MM 2024 First author

[C5] Non-uniform Timestep Sampling: Towards Faster Diffusion Model Training

Tianyi Zheng, Cong Geng, Peng-Tao Jiang, Ben Wan, Hao Zhang, Jinwei Chen, Jia Wang, Bo Li

[Paper] ACM International Conference on Multimedia (MM) 2024

ECCV 2024 First author

[C6] Beta-Tuned Timestep Diffusion Model

Tianyi Zheng, Peng-Tao Jiang, Ben Wan, Hao Zhang, Jinwei Chen, Jia Wang, Bo Li

[Paper] European Conference on Computer Vision (ECCV) 2024

ICASSP 2024 Oral First author

[C7] FAMIM: A Novel Frequency-Domain Augmentation Masked Image Model Framework for Domain Generalizable Face Anti-Spoofing

Tianyi Zheng, Qinji Yu, Zhaoyu Chen, Jia Wang

[Paper] IEEE ICASSP 2024 Oral

Journal

TMLR 2026 First author

[J7] REPA-FPO: A Fisher Policy Optimization for Efficient Flow Matching Training

Tianyi Zheng, Fengxiang Yang, Yijie Zhong, Jiayang Gao, Lv Tang, Jinwei Chen, Peng-Tao Jiang, Jia Wang, Bo Li

[Paper] Transactions on Machine Learning Research (TMLR) 2026

T-PAMI 2026 First author

[J1] Bidirectional Beta-Tuned Diffusion Model

Tianyi Zheng, Jiayang Zou, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Jia Wang, Bo Li

[Paper] IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2026

NN 2025

[J2] Gradient Flow-Based Iterative Pruning for Efficient and High-Quality Lightweight Diffusion Models

Ben Wan, Tianyi Zheng, Yuxiao Wang, Jia Wang

[Paper] Neural Networks (NN) 2025

NC 2025 First author

[J3] EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-Spoofing

Tianyi Zheng, Bo Li, Shuang Wu, Ben Wan, Guodong Mu, Shice Liu, Shouhong Ding, Jia Wang

[Paper] Neurocomputing (NC) 2025

NC 2025

[J4] Enhancing the Accuracy of Generative Adversarial Networks with Fokker-Planck Equations

Ben Wan, Tianyi Zheng, Zhaoyu Chen, Jia Wang

[Paper] Neurocomputing (NC) 2025

NN 2025

[J5] EBM-WGF: Training Energy-based Models with Wasserstein Gradient Flow

Ben Wan, Cong Geng, Tianyi Zheng, Jia Wang

[Paper] Neural Networks (NN) 2025

T-IFS 2024 First author

[J6] MFAE: Masked Frequency Autoencoders for Domain Generalization Face Anti-Spoofing

Tianyi Zheng, Bo Li, Shuang Wu, Ben Wan, Guodong Mu, Shice Liu, Shouhong Ding, Jia Wang

[Paper] IEEE Transactions on Information Forensics and Security (T-IFS) 2024

Preprint

[P5] MIEScore: Human-Aligned Evaluation for Multi-Source Image Editing

Zitong Xu, Huiyu Duan, Xinyun Zhang, Weifei Xiong, Tianyi Zheng, Xiongkuo Min, Qiang Hu, Zhengxue Cheng, Bo Li, Guangtao Zhai

[Paper] arXiv 2026

[P4] EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement

Zitong Xu, Huiyu Duan, Yifei Nie, Mingda Du, Sijing Wu, Xiongkuo Min, Tianyi Zheng, Jian Zhang, Shusong Xu, Jinwei Chen, Bo Li, Guangtao Zhai

[Paper] arXiv 2026

[P2] InfoTok: Regulating Information Flow for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs

Lv Tang, Tianyi Zheng, Bo Li, Xingyu Li

[Paper] arXiv 2026

[P1] Towards Generalizable Data Protection With Transferable Unlearnable Examples

Bin Fang, Bo Li, Shuang Wu, Tianyi Zheng, Shouhong Ding, Ran Yi, Lizhuang Ma

[Paper] arXiv 2023

Research Experiences

BlueImage Lab@vivo

WorkResearcher

Jul. 2025 - Present

Focused on improving diffusion model architectures, including training efficiency, sampling quality, and controllability.
Explored multimodal large language models (MLLMs), with emphasis on visual understanding and generation alignment.

Advertising Marketing Services (AMS)@Tencent

InternIntern

Mar. 2025 - Jun. 2025

Investigated controllable image generation, focusing on the automated generation of advertising assets.
Explored techniques for achieving fine-grained control over generative outputs in diffusion-based frameworks.

BlueImage Lab@vivo

InternResearch Intern

Oct. 2023 - Mar. 2025

Investigated the application and improvement of diffusion models for image generation and edit tasks.

Youtu Lab@Tencent

InternResearch Intern

Jan. 2022 - Oct. 2023

Conducted research on computer vision algorithms with a focus on self-supervised learning and representation learning for visual understanding.
Explored domain generalization methods to improve model robustness across different data distributions, particularly for face anti-spoofing.

AI Lab@Midea

InternResearch Intern

Jul. 2021 - Dec. 2021

Explored efficient inference techniques for deep learning models.

Honors & Awards

BYD Scholarship, Shanghai Jiao Tong University 2025

Outstanding Graduate Scholarship, Xidian University 2020

Outstanding Student Scholarship, Xidian University 2017, 2018, 2019

Academic Services

Area Chairs & Senior Program Committee

AAAI Conference on Artificial Intelligence (AAAI)

Conference Reviewer

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

European Conference on Computer Vision (ECCV)

European Conference on Artificial Intelligence (ECAI)

IEEE/CVF International Conference on Computer Vision (ICCV)

The British Machine Vision Conference (BMVC)

Conference on Neural Information Processing Systems (NeurIPS)

International Conference on Learning Representations (ICLR)

International Conference on Machine Learning (ICML)

AAAI Conference on Artificial Intelligence (AAAI)

International Joint Conference on Artificial Intelligence (IJCAI)

ACM International Conference on Multimedia (ACM MM)

International Conference on Artificial Intelligence and Statistics (AISTATS)

International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Journal Reviewer

Neural Networks (NN)

Neurocomputing (NC)

International Journal of Computer Vision (IJCV)

Pattern Recognition (PR)

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Knowledge-Based Systems (KBS)

Transactions on Machine Learning Research (TMLR)

Teaching Assistant

EE453: Elements of Information Theory, Shanghai Jiao Tong University

Biography

Work & Intern Experience

Education

Research Interests

News Recent Updates

Publications Selected Full

Conference

Journal

Preprint

Research Experiences

Honors & Awards

Collaborators

Academic Services

Publications