I am currently a research scientist at ByteDance Seed. Before that, I received my B.E. degree from Wuhan University in 2024.

PROJECTS

Seedream 4.5 (World #2 in Edit at Release)

Seedream 4.0 (World #1 in T2I & Edit at Release)

Seedream 3.0 (World #1 in T2I at Release)

Allegro

PUBLICATIONS

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Technical Report
ByteDance Seed Seedream Team
[paper] [project] [leaderboard] [Time Magazine] [SCMP] [try]

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

NeurIPS, 2025
Wei Chen, Xin Yan, Bin Wen, Fan Yang, Tingting Gao, Di Zhang, Long Chen
[paper] [code]

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation

CVPR, 2025
Xin Yan, Yuxuan Cai, Qiuyue Wang, Yuan Zhou, Wenhao Huang, Huan Yang
[project] [paper] [code] [Allegro]

RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text

ICCV, 2025
Jiaben Chen, Xin Yan, Yihang Chen, Siyuan Cen, Qinwei Ma, Haoyu Zhen, Kaizhi Qian, Lie Lu, Chuang Gan
[project] [paper] [code]

3D-VLA: A 3D Vision-Language-Action Generative World Model

ICML, 2024
Haoyu Zhen, Xiaowen Qiu, Peihao Chen, Jincheng Yang, Xin Yan, Yilun Du, Yining Hong, Chuang Gan
[project] [paper] [code] [twitter]

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos

ICML, 2024
Zhicheng Zheng*, Xin Yan*, Zhenfang Chen*, Jingzhou Wang, Qin Zhi Eddie Lim, Joshua B. Tenenbaum, Chuang Gan
[project] [paper] [code] [dataset]

Centroid-centered Modeling for Efficient Vision Transformer Pre-training

PRCV, 2024
Xin Yan, Zuchao Li, Lefei Zhang, Bo Du, Dacheng Tao
[paper] [code]

EXPERIENCE

2025-2025    Seed @ ByteDance

2024-2025    Yuntian Group @ UWaterloo

2024-2025    01.AI

2023-2024    MIT-IBM Watson AI Lab

2022-2023    Wuhan University