Yuying Ge 葛玉莹

[email protected]

Google Sholar

Github

Shenzhen, China

Biography

I am currently a Staff Research Scientist at XPENG Robotics, exploring cutting-edge technologies of embodied AI. Previously, I spent two wonderful years at Tencent ARC Lab and Tencent AI Lab, working on multimodal foundation models. In Aug 2023, I got my Ph.D. degree from the Department of Computer Science, The University of Hong Kong, under the supervision of Prof. Ping Luo. I was also a visiting student at UCSD, working with Prof. Xiaolong Wang. We are actively looking for full-time researchers, engineers and interns to work on related topics. Please feel free to reach out if you are interested.

News

[07/2025] We release ARC-Hunyuan-Video, a multimodal model for structured comprehension of real-world short videos.
[06/2025] We release GRPO-CARE, introducing consistency-aware GRPO for multimodal reasoning.
[06/2025] We release FlowAlign, using flow-based models to align learnable latent spaces to target distributions.
[06/2025] We release AnimeShooter, multi-shot animation dataset for reference-guided video generation.
[05/2025] We release Video-Holmes, evaluating MLLMs for complex video reasoning like Holmes.
[04/2025] We release AnimeGamer, transforming characters from anime films into interactive entities with a MLLM.
[04/2025] We release SEED-Bench-R1, exploring the effects of RL on video understanding with hierarchical evaluation.
[03/2025] We release GenHancer, using imperfect generative models for enhanced vision-centric representations.
[12/2024] We release Divot, a diffusion-powered video tokenizer for unified comprehension and generation.
[12/2024] We release DiCoDe for autoregressive video generation with LLMs.
[12/2024] We release MoTo, Latent Motion Tokens for autoregressive video pretraining to enhance robot manipulation.
[12/2024] We release EgoPlan-Bench2, evaluating planning capabilities of MLLMs across various real-world scenarios.
[07/2024] We release SEED-Story for Multimodal Long Story Generation based on SEED-X.
[04/2024] We release SEED-X, the latest in our SEED series, which unifies multi-granularity comprehension and generation.
[02/2024] SEED-Bench is accepted by CVPR 2024.
[01/2024] SEED-LLaMA is accepted by ICLR 2024.
[12/2023] We release EgoPlan-Bench, which evaluates egocentric embodied planning of MLLMs.
[11/2023] We release SEED-Bench-2, evaluating the hierarchical capabilities of MLLMs.
[10/2023] We release an online gradio demo of SEED-LLaMA.
[10/2023] We release the technical report of SEED-LLaMA, which is empowered by the improved SEED-2 tokenizer.
[08/2023] We release SEED-Bench, the most comprehensive MLLM benchmark to date.
[07/2023] We release our SEED. Stay tuned for more updates.
[02/2023] Three papers were accepted by CVPR 2023.
[07/2022] One paper was accepted by ECCV 2022.
[03/2022] One paper was accepted by CVPR 2022 as oral.
[11/2021] One paper was accepted by IEEE TIP.
[03/2021] Two papers were accepted by CVPR 2021.
[03/2019] One paper was accepted by CVPR 2019.

SEED Series

Since July 2023, our SEED Series has been pioneering the exploration of Multimodal Foundation Models for Unified Comprehension and Generation, along with developing cutting-edge Benchmarks. We continuously explore real-world applications of unified foundation models, expand into broader modalities, and enhance advanced capabilities like multimodal interleaved generation, and reasoning. All models and data are open-sourced.

Selected Publications

( *equal contribution ^#corresponding author / project lead )

ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts
Yuying Ge, Yixiao Ge, Chen Li, Teng Wang, Junfu Pu, Yizhuo Li, Lu Qiu, Jin Ma, Lisheng Duan, Xinyu Zuo, Jinwen Luo, Weibo Gu, Zexuan Li, Xiaojing Zhang, Yangyu Tao, Han Hu, Di Wang, Ying Shan
arXiv preprint, 2025. [Paper] [Project] [Code] [Model]
GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
Yi Chen, Yuying Ge^#, Rui Wang, Yixiao Ge, Junhao Cheng, Ying Shan, Xihui Liu
arXiv preprint, 2025. [Paper] [Code] [Model]
Aligning Latent Spaces with Flow Priors
Yizhuo Li, Yuying Ge^#, Yixiao Ge, Ying Shan, Ping Luo
arXiv preprint, 2025. [Paper] [Code] [Project]
AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation
Lu Qiu, Yizhuo Li, Yuying Ge^#, Yixiao Ge, Ying Shan, Xihui Liu
arXiv preprint, 2025. [Paper] [Code] [Project]
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
Junhao Cheng, Yuying Ge^#, Teng Wang, Yixiao Ge, Jing Liao, Ying Shan
arXiv preprint, 2025. [Paper] [Code] [Project]
AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction
Junhao Cheng, Yuying Ge^#, Yixiao Ge, Jing Liao, Ying Shan
ICCV, 2025. [Paper] [Code] [Project]
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
Yi Chen, Yuying Ge^#, Rui Wang, Yixiao Ge, Lu Qiu, Ying Shan, Xihui Liu
arXiv preprint, 2025. [Paper] [Code] [Dataset]
GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers
Shijie Ma, Yuying Ge^#, Teng Wang, Yuxin Guo, Yixiao Ge, Ying Shan
ICCV, 2025. [Paper] [Code] [Project]
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
Yuying Ge, Yizhuo Li, Yixiao Ge, Ying Shan
CVPR, 2025. [Paper] [Code]
DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models
Yizhuo Li, Yuying Ge^#, Yixiao Ge, Ping Luo, Ying Shan
arXiv preprint, 2024. [Paper] [Project] [Code]
Moto: Latent Motion Token as the Bridging Language for Robot Manipulation
Yi Chen, Yuying Ge^#, Yizhuo Li, Yixiao Ge, Mingyu Ding, Ying Shan, Xihui Liu
ICCV, 2025. [Paper] [Code] [Project]
EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios
Lu Qiu, Yuying Ge^#, Yi Chen, Yixiao Ge, Ying Shan, Xihui Liu
arXiv preprint, 2024. [Paper] [Code] [Project]
SEED-Story: Multimodal Long Story Generation with Large Language Model
Shuai Yang, Yuying Ge^#, Yang Li, Yukang Chen, Yixiao Ge, Ying Shan, Yingcong Chen
arXiv preprint, 2024. [Paper] [Code]
EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning
Yi Chen, Yuying Ge^#, Yixiao Ge, Mingyu Ding, Bohao Li, Rui Wang, Ruifeng Xu, Ying Shan, Xihui Liu
arXiv preprint, 2024. [Paper] [Code] [Project]
SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
Yuying Ge*, Sijie Zhao*, Jinguo Zhu*, Yixiao Ge, Kun Yi, Lin Song, Chen Li, Xiaohan Ding, Ying Shan
arXiv preprint, 2024. [Paper] [Code] [Demo]
SEED-Bench: Benchmarking Multimodal Large Language Models
Bohao Li*, Yuying Ge*, Yixiao Ge, Guangzhi Wang, Rui Wang, Ruimao Zhang, Ying Shan
CVPR, 2024. [Paper] [Code] [Data] [Leaderboard]
Making LLaMA SEE and Draw with SEED Tokenizer
Yuying Ge*, Sijie Zhao*, Ziyun Zeng, Yixiao Ge, Chen Li, Xintao Wang, Ying Shan
ICLR, 2024. [Paper] [Code]
Planting a SEED of Vision in Large Language Model
Yuying Ge*, Yixiao Ge*, Ziyun Zeng, Xintao Wang, Ying Shan
Technical Report, 2023. [Paper] [Code]
Policy Adaptation from Foundation Model Feedback
Yuying Ge, Annabella Macaluso, Li Erran Li, Ping Luo, Xiaolong Wang
CVPR, 2023. [Paper] [Project] [Code]
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Ziyun Zeng*, Yuying Ge*, Xihui Liu, Bin Chen, Ping Luo, Shu-Tao Xia, Yixiao Ge
CVPR, 2023. [Paper] [Code]
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval
Yuying Ge, Yixiao Ge, Xihui Liu, Alex Jinpeng Wang, Jianping Wu, Ying Shan, Xiaohu Qie and Ping Luo
ECCV, 2022. [Paper] [Code]
Bridging Video-text Retrieval with Multiple Choice Questions
Yuying Ge, Yixiao Ge, Xihui Liu, Dian Li, Ying Shan, Xiaohu Qie and Ping Luo
CVPR, 2022 (oral). [Paper] [Project] [Code]
Parser-Free Virtual Try-on via Distilling Appearance Flows
Yuying Ge, Yibing Song, Ruimao Zhang, Chongjian Ge, Wei Liu, and Ping Luo
CVPR, 2021. [Paper] [Code]
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
Yuying Ge, Ruimao Zhang, Xiaogang Wang, Xiaoou Tang, and Ping Luo
CVPR, 2019. [Paper] [Data]

Education

Ph.D., Department of Computer Science, The University of Hong Kong, 2019 - 2023
Bachelor, University of Electronic Science and Technology of China (UESTC) (ranking 1/525), 2014 - 2018

Experiences

Staff Research Scientist at XPENG Robotics, 2025 - Present
Senior Researcher in Tencent ARC Lab, 2024 - 2025
Senior Researcher in Tencent AI Lab, 2023 - 2024
Intern in Tencent ARC Lab, 2021 - 2022
Intern in Tencent AI Lab, 2020 - 2021
Research Assistant in Multimedia Lab (MMLab), The Chinese University of Hong Kong, 2018 - 2019
Intern in SenseTime Research, 2017 - 2018

Academic Activities

Reviewer for CVPR, ICLR, ICML, NeurIPS, ECCV, ICCV, TPAMI, TNNLS, TMM, TVCJ
Organizer of DeepFashion2 Challenge Clothes Landmark Detection and Clothes Retrieval in 2019, 2020
Organizer of Third Workshop on Computer Vision for Fashion, Art and Design in CVPR, 2020
Organizer of Second Workshop on Computer Vision for Fashion, Art and Design in ICCV, 2019