Research & Academic Profile

Xiangyue Zhang 章湘粤

Ph.D. Student · Mechano-Informatics, The University of Tokyo

[email protected] xiangyuezhang.com Google Scholar GitHub LinkedIn

Research interests Embodied AI, 3D/2D human motion generation, co-speech gesture generation, and world models.

Education

Research Experience

Publications

First-author Publications

  1. StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring

    Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Kaixing Yang, and Steven Hoi

    ECCV 2026arXivCodeProject

  2. Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints

    Xiangyue Zhang, Jianfang Li, Jianqiang Ren, and Jiaxu Zhang

    AAAI 2026arXivCodeProject

  3. SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis

    Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Ziqiang Dang, Jianqiang Ren, Liefeng Bo, and Zhigang Tu

    ICCV 2025arXivCodeProject

  4. EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation

    Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Jianqiang Ren, Liefeng Bo, and Zhigang Tu

    ACM MM 2025arXivCodeProject

  5. Robust 2D Skeleton Action Recognition via Decoupling and Distilling 3D Latent Features

    Xiangyue Zhang, Yifan Jia, Jiaxu Zhang, Yijie Yang, and Zhigang Tu

    T-CSVT 2025

Co-author Publications

  1. Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation

    Yi Liu, Xiangyue Zhang, Jianfang Li, Jia Ma, Yisheng He, and Jianqiang Ren

    NeurIPS 2026arXivProject

  2. MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

    Kaixing Yang, Jiashu Zhu, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Puwei Wang, Jiahong Wu, Xiangxiang Chu, Hongyan Liu, and Jun He

    SIGGRAPH 2026arXivCodeProject

  3. OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data

    Kaixing Yang, Jiashu Zhu, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Chubin Chen, Puwei Wang, Jiahong Wu, Xiangxiang Chu, Hongyan Liu, and Jun He

    ECCV Spotlight 2026PaperCodeProject

  4. FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation

    Kaixing Yang, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Puwei Wang, Jun He, and Hongyan Liu

    ECCV 2026arXivCodeProject

Preprints

  1. World2Motion: Turning Video World Models into 3D Human Motion Generators

    Fangyuan Tu, Xiangyue Zhang, Yiyi Cai, Yichen Peng, Kunhang Li, Bo Zheng, Zhixiang Wang, Kaipeng Zhang, Erwin Wu, Haoran Xie, Haiyang Liu

    Preprint 2026arXivProject

  2. FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation

    Yiyi Cai, Yuhan Wu, Kunhang Li, Tu Fangyuan, Xiangyue Zhang, Qiaoge Li, Zhixiang Wang, Kaipeng Zhang, Haiyang Liu

    Preprint 2026arXivCodeProject

Open-Source Systems

NextTransformer: An Open Framework and Fair Benchmark for Next-Generation Transformer Architectures

A shared training framework and compute-matched benchmark for comparing Transformer architectures.

WebsiteCodeDocs

Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring

An open-source framework for autonomous deep learning experimentation, monitoring, and iterative refinement.

WebsiteCodearXiv

Awards & Honors

Academic Service

Reviewer: ICLR, NeurIPS, AAAI, ACM MM, T-CSVT, PR