Profile image
Kaipeng Zhang
Researcher
Shanghai AI Lab

About Me

I am a researcher in Shanghai AI Lab and working on MLLM and video generation.

Before coming to Shanghai AI Lab, I received my PhD degree in 2022 from The University of Tokyo, supervised by Prof. Yoichi Sato, M.S. degree in 2018 from National Taiwan University supervised by Prof. Winston Hsu, and B.E. degree in 2016 from Donghua University. I was a researcher in SenseTime and consultant in ULSee. I also did research internships at Microsoft Research Asia, Tencent AI Lab, and MMLAB of SIAT. I work closely with Dr. Yu Qiao, Dr. Ping Luo, Dr. Tong He, and Dr. Wenqi Shao.

I like Chinese/Japan anime, Chinese costume drama, and games. I'm looking for interns interested in world models and AI-native games, especially those interested in developing games like Sword Art Online and Log Horizon. Please send me your resume.

Former Interns [First-author papers done in internship] (University -> The next place after internship)
Chuanhao Li [1 NeurIPS] (BIT PhD -> Shanghai AI Lab)
Yue Yang [1 ICASSP, 1 ICML, 1 ICLR] (SJTU PhD)
Hao Zhang [1 IJCV, 1 TIFS] (XJTU PhD)
Yuqi Lin [1 AAAI, 1 ICLR] (ZJU PhD)
Yefei He [1 ICML, 2 ICCV] (ZJU PhD)
Zhaopan Xu [1 ACL Findings, 2 preprints] (HIT Phd)
Yansheng Qiu [2 preprints] (WHU PhD)
Wenshuo Peng [1 AAAI, 1 EMNLP Findings, 1 IJCV] (Tsinghua Master -> Baidu)
Ziyao Guo [1 ICLR, 1 preprint] (Xidian Master -> NUS Phd)
Lirui Zhao [1 CVPR] (XMU Master -> HKU Phd)
Kaining Ying [1 ICML] (ZJUT Master -> FDU Phd)
Pengfei Zhou [1 CVPR, 1 NeurIPS, 1 preprint] (UCAS Master -> NUS PhD)
Ming Li [1 NeurIPS] (UTokyo Master -> UMD PhD)
Tianle Zhang [1 NeurIPS] (UESTC Bachlor -> NTU Phd)
Yuxuan Xie [1 IJCAI] (SJTU Bachlor -> SJTU Master)
Tianhua Li [1 IJCAI] (SJTU Bachlor -> SJTU Master)
Yanqing Liu (ZJU Bachlor -> UCSC Phd)
Haoquan Zhang [1 preprint] (SCUT Bachlor -> CUHK Phd)
Current Interns
Updating

Recent Publications (2024 & 2025)


[Recent Technical Report]
[World Model]Yume: An Interactive World Generation Model

[Agent]PyVision: Agentic Vision with Dynamic Tooling

[Agent]AI Idea Bench 2025: AI Research Idea Generation Benchmark

[Image Generation]IA-T2I: Internet-Augmented Text-to-Image Generation

[Image Generation]SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model

[Reasoning]MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models

[Reasoning]Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans

[MLLM]A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation

[MLLM]ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability

[Conference Papers]
[NeurIPS 2025 Spotlight]Think or not think: A study of explicit thinking in rule-based visual reinforcement fine-tuning
Ming Li, Jike Zhong, Shitian Zhao, Yuxiang Lai, Haoquan Zhang, Wang Bill Zhu, Kaipeng Zhang†
[NeurIPS 2025] Sekai: A Video Dataset towards World Exploration
Zhen Li, Chuanhao Li, Xiaofeng Mao, Shaoheng Lin, Ming Li, Shitian Zhao, xu Zhao Pan, Xinyue Li, Yukang Feng, Jianwen Sun, Zizhen Li, Fanrui Zhang, Jiaxin Ai, Zhixiang Wang, Yuwei Wu†, Tong He, Yunde Jia, Kaipeng Zhang†

[NeurIPS 2025] Neural-Driven Image Editing
Pengfei Zhou, Jie Xia, Xiaopeng Peng, Wangbo Zhao, Zilong Ye, Zekai Li, Suorong Yang, Jiadong Pan, Yuanxiang Chen, Ziqiao Wang, Kai Wang, Qian Zheng, Xiaojun Chang, Gang Pan, Shurong Dong†, Kaipeng Zhang†, Yang You
[NeurIPS 2025] REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Ziqiao Wang, Wangbo Zhao, Yuhao Zhou, Zekai Li, Zhiyuan Liang, Mingjia Shi, Xuanlei Zhao, Pengfei Zhou, Kaipeng Zhang†, Zhangyang Wang, Kai Wang†, Yang You
[EMNLP 2025] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
Zizhen Li, Chuanhao Li, Yibin Wang, Qi Chen, Diping Song, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Kaipeng Zhang†
[ICCV 2025] ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges
Jiaxin Ai, Pengfei Zhou, xu Zhao Pan, Ming Li, Fanrui Zhang, Zizhen Li, Jianwen Sun, Yukang Feng, Baojin Huang, Zhongyuan Wang†, Kaipeng Zhang†
[ICCV 2025] Neighboring Autoregressive Modeling for Efficient Visual Generation
Yefei He, Yuanyu He, Shaoxuan He, Feng Chen, Hong Zhou†, Kaipeng Zhang†, Bohan Zhuang†
[ICCV 2025] ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity
Yefei He, Feng Chen, Jing Liu, Wenqi_Shao, Hong Zhou†, Kaipeng Zhang†, Bohan Zhuang
[ICCV 2025] LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Jiahao Wang, Ning Kang, Lewei Yao, Mengzhao Chen, Chengyue Wu, Songyang Zhang, Shuchen Xue, Yong Liu, Taiqiang Wu, Xihui Liu, Kaipeng Zhang, Shifeng Zhang, Wenqi Shao†, Zhenguo Li†, Ping Luo
[ICCV 2025] GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
Quanfeng_Lu, Wenqi Shao†, Zitao Liu, Lingxiao Du, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, Ping Luo†
[ACL Findings 2025] MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
Zhaopan Xu, Pengfei Zhou, Jiaxin Ai, Wangbo Zhao, Kai Wang, Xiaojiang Peng, Wenqi Shao, Hongxun Yao†, Kaipeng Zhang†
[ACL 2025] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
Mengzhao Chen, Wenqi Shao†, Peng Xu, Jiahao Wang, Peng Gao, Kaipeng Zhang, Ping Luo†
[ICML 2025] ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality
Yefei He, Feng Chen, Yuanyu He, Shaoxuan He, Hong Zhou†, Kaipeng Zhang†, Bohan Zhuang,
[ICML 2025] Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
Fanqing Meng, Jiaqi Liao, Xinyu Tan, Wenqi Shao†, Quanfeng Lu, Kaipeng Zhang, Yu Cheng, Dianqi Li, Ping Luo†
[IJCAI 2025] TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts
Yuxuan Xie, Tianhua Li, Wenqi Shao, Kaipeng Zhang†
[CVPR 2025 Oral] OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
Pengfei Zhou*, Xiaopeng Peng*, Jiajun Song, Chuanhao Li, Zhaopan Xu, Yue Yang, Ziyao Guo, Hao Zhang, Yuqi Lin, Yefei He, Lirui Zhao, Shuo Liu, Tianhua Li, Yuxuan Xie, Xiaojun Chang, Yu Qiao, Wenqi Shao,, Ping Luo, Kaipeng Zhang†
[ICLR 2025 Oral] Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
Yue Yang*, Shuibo Zhang*, Wenqi Shao†, Kaipeng Zhang†, Yi Bin, Yu Wang, Ping Luo†
[ICLR 2025] SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
Yuqi Lin, Hengjia Li, Wenqi Shao, Zheng Yang†, Jun Zhao, Xiaofei He, Ping Luo, Kaipeng Zhang†
[ICLR 2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
Fanqing Meng*, Chuanhao Li*, Jin Wang*, Quanfeng Lu, Hao Tian, Tianshuo Yang, Jiaqi Liao, Xizhou Zhu, Jifeng Dai, Yu Qiao, Ping Luo, Kaipeng Zhang†, Wenqi Shao†
[NeurIPS 2024 Spotlight] ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models
Shuo Liu, Kaining Ying, Hao Zhang, Yue Yang, Yuqi Lin, Tianle Zhang, Chuanhao Li, Yu Qiao, Ping Luo, Wenqi Shao†, Kaipeng Zhang†
[NeurIPS 2024] SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
Chuanhao Li, Zhen Li, Chenchen Jing, Shuo Liu, Wenqi Shao, Yuwei Wu, Ping Luo, Yu Qiao, Kaipeng Zhang†
[NeurIPS 2024] Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality
Tianle Zhang, Langtian Ma, Yuchen Yan, Yuchen Zhang, Kai Wang, Yue Yang, Ziyao Guo, Wenqi Shao, Yang You, Yu Qiao, Ping Luo, Kaipeng Zhang†
[NeurIPS 2024] Needle In A Multimodal Haystack
Weiyun Wang, Shuibo Zhang, Yiming Ren, Yuchen Duan, Tiantong Li, Shuo Liu, Mengkang Hu, Zhe Chen, Kaipeng Zhang, Lewei Lu, Xizhou Zhu, Ping Luo, Yu Qiao, Jifeng Dai, Wenqi Shao†, Wenhai Wang†
[NeurIPS 2024] Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
Le Zhuo*, Ruoyi Du*, Han Xiao*, Yangguang Li*, Dongyang Liu*, Rongjie Huang*, Wenze Liu*, Lirui Zhao, Fu-Yun Wang, Zhanyu Ma, Xu Luo, Zehan Wang, Kaipeng Zhang, Xiangyang Zhu, Si Liu, Xiangyu Yue, Dingning Liu, Wanli Ouyang, Ziwei Liu, Yu Qiao†, Hongsheng Li†, Peng Gao†
[ICML 2024] Towards Implicit Prompt For Text-To-Image Models
Yue Yang, Yuqi Lin, Hong Liu, Wenqi Shao, Runjian Chen, Hailong Shang, Yu Wang, Yu Qiao, Kaipeng Zhang† and Ping Luo†
[ICML 2024] MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Kaining Ying*, Fanqing Meng*, Jin Wang*, Zhiqian Li, Han Lin, Yue Yang, Hao Zhang, Wenbo Zhang, Yuqi Lin, Shuo Liu, Jiayi Lei, Quanfeng Lu, Cunjian Chen, Peng Xu, Renrui Zhang, Haozhe Zhang, Peng Gao, Yali Wang, Yu Qiao, Ping Luo, Kaipeng Zhang† and Wenqi Shao†
[ICML 2024] SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
Peng Gao*†, Renrui Zhang*, Chris Liu*, Longtian Qiu*, Siyuan Huang*, Weifeng Lin*, Shitian Zhao, Shijie Geng, Ziyi Lin, Peng Jin, Kaipeng Zhang, Wenqi Shao, Chao Xu, Conghui He, Junjun He, Hao Shao, Pan Lu, Hongsheng Li† and Yu Qiao
[CVPR 2024] DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model
Lirui Zhao*, Yue Yang*, Kaipeng Zhang‡*, Wenqi Shao‡*, Yuxin Zhang, Yu Qiao, Ping Luo, Rongrong Ji†
[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language
Jiaming Han, Kaixiong Gong, Yiyuan Zhang, Jiaqi Wang, Kaipeng Zhang, Dahua Lin, Yu Qiao, Peng Gao, Xiangyu Yue†
[NAACL Findings 2024] T3M: Text Guided 3D Human Motion Synthesis from Speech
Wenshuo Peng, Kaipeng Zhang†, Sai Qian Zhang†
[ACL Findings 2024] ChartAssistant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning
Fanqing Meng, Wenqi Shao†, Quanfeng Lu, Peng Gao, Kaipeng Zhang, Yu Qiao, Ping Luo†
[ICLR 2024] Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
Ziyao Guo, Kai Wang, George Cazenavette, Hui Li, Kaipeng Zhang†, Yang You†
[ICLR 2024] OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Wenqi Shao*, Mengzhao Chen*, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, Ping Luo†
[AAAI 2024]Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification
Wenshuo Peng, Kaipeng Zhang†, Yue Yang, Hao Zhang, Yu Qiao
[AAAI 2024]TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training
Yuqi Lin, Minghao Chen†, Kaipeng Zhang†, Hengjia Li, Mingming Li, Zheng Yang, Dongqin Lv, Binbin Lin, Haifeng Liu, Deng Cai
[ICASSP 2024]Align, Adapt and Inject: Audio-Guided Image Generation, Editing and Stylization
Yue Yang, Kaipeng Zhang†, Yuying Ge, Wenqi Shao, Zeyue Xue, Yu Qiao, Ping Luo†

[Journal Papers]
[IJCV 2025]HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion
Wenshuo Peng, Kaipeng Zhang†
[IJCV 2024]Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching
Hao Zhang, Lumin Xu, Shenqi Lai, Wenqi Shao, Nanning Zheng†, Ping Luo, Yu Qiao, Kaipeng Zhang†
[TPAMI 2024]LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models
Peng Xu*, Wenqi Shao†*, Kaipeng Zhang*, Peng Gao*, Shuo Liu, Meng Lei, Fanqing Meng, Siyuan Huang, Yu Qiao, Ping Luo†
[TIFS 2024]B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions
Hao Zhang, Wenqi Shao, Hong Liu, Yongqiang Ma, Ping Luo, Yu Qiao, Nanning Zheng†, Kaipeng Zhang†
[TBigData 2024]Tiny LVLM-eHub: Early Multimodal Experiments with Bard
Wenqi Shao*, Yutao Hu*, Peng Gao*, Meng Lei*, Kaipeng Zhang, Fanqing Meng, Peng Xu, Siyuan Huang, Hongsheng Li, Yu Qiao†, Ping Luo†
[TCSVT 2024]HF-HRNet: a simple hardware friendly high-resolution network
Hao Zhang, Yujie Dun, Yixuan Pei, Shenqi Lai, Chengxu Liu, Kaipeng Zhang, Xueming Qian†
[Pattern Recognition 2024]FMGNet: An efficient feature-multiplex group network for real-time vision task
Hao Zhang, Yongqiang Ma, Kaipeng Zhang, Nanning Zheng†, Shenqi Lai†

[Tutorial]
[CVPR 2025 Tutorial]From Multimodal LLM to Human-level AI: Evaluations and Benchmarks

Education

Ph.d. in CS, The University of Tokyo, Tokyo, Japan
Apr. 2019 - Mar. 2022
M.S. in CS, National Taiwan University, Taipei, Taiwan
Sep. 2016 - Aug. 2018
B.Eng. in CS, Donghua University, Shanghai, China
Sep. 2012 - July 2016

Selected Awards and Competitions

  • WAIC Young Outstanding Paper Award, 2022
  • World's TOP 2% Scientists (published by Stanford University), 2020 & 2021 & 2022 & 2023
  • JSPS Research Fellowships for Young Scientists, 2020
  • Tencent Rhino-Bird Elite Training Program, 2020
  • MSRA Fellowship Nomination Award, 2019
  • Emotion Recognition in the Wild: Engagement Prediction (ICMI 2019 Grand Challenge), 3rd place
  • Emotion Recognition in the Wild: Group-based Cohesion Prediction (ICMI 2019 Grand Challenge), 2nd place
  • Disguised Faces in the Wild Challenge (in conjunction with CVPR 2018), 1st place
  • Emotion Recognition in the Wild: Group-level emotion recognition (ICMI 2018 Grand Challenge), 2nd place
  • Emotion Recognition in the Wild: Group-level emotion recognition (ICMI 2017 Grand Challenge), 1st place
  • ChaLearn Looking at People Challenge: Accessories Classification (in conjunction with CVPR 2016), 1st place
  • ChaLearn Looking at People Challenge: Smile and Gender Classification (in conjunction with CVPR 2016), 1st place
  • Outstanding Undergraduate Thesis, 2016

    • Academic Service

  • Area Chair of ICLR
  • Senior program committee of IJCAI and AAAI
  • Reviewer/Program committee of NeurIPS, ICML, ICLR, AAAI, ICCV, ECCV, CVPR, BMVC, WACV and ACCV
  • Reviewer of TPAMI, TIP, TCSVT, TNNLS, TMM, TIFS, Neurocomputing, Pattern Recognition, and SPL

    • Work Experience

    Researcher
    Shanghai AI Lab
    OpenGVLab
    Shanghai, China
    May. 2022 - Present
    Researcher
    SenseTime
    Research Institute
    Shenzhen, China
    Sept. 2018 - Mar. 2019
    Intern
    MSRA
    Visual Computing Group
    Beijing, China
    Jan. 2018 - Jul. 2018
    Consultant
    ULSee
    Face Team
    Hangzhou, China
    Oct. 2016 - Mar. 2018
    Intern
    Tencen
    AI Lab & AI Advertisement Department
    Shenzhen, China
    Jul. 2017 - Aug. 2017
    Sep. 2020 - Feb. 2021
    Visiting Student
    Shenzhen Institutes of Advanced Technology
    Multimedia Research Center
    Shenzhen, China
    Jul. 2015 - Aug. 2016

    Copyright © Kaipeng Zhang 2017

    Template from Jason Lai