😃 Greetings!

I am currently a Research Scientist at ByteDance GenAI, working with Zehuan Yuan, Xiang Yin, and Yi Ren on generative video and multimodal intelligence.

I received my Ph.D. from Zhejiang University, under the supervision of Prof. Weidong Geng. During my doctoral studies, I undertook a visiting Ph.D. program at Nanyang Technological University (NTU), supervised by Prof. Eng Siong Chng.

My research aims to build controllable and expressive generative systems that connect visual content, body motion, music, speech, and audio-video intelligence. My current interests include:

  • 🎬 Generative video: lifelike audio-video generation, reference-based animation, and multimodal generation.
  • 🕺 Human motion and embodied intelligence: motion synthesis and comprehension, controllable motion generation, and streaming motion modeling.
  • 🎵 Cross-modal creativity: learning the relationships among dance, music, visual content, and embodied behavior.

🔥 News

  • 2026.06 : 📑 VersatileMotion was accepted to ECCV 2026.
  • 2026.03 : 🚀 PRISM was released for streaming human motion generation with per-joint latent decomposition.
  • 2026.02 : 🚀 ALIVE was introduced as a unified model for lifelike audio-video generation and animation.
  • 2024.07 : 📑 Dance2MIDI was published in Computational Visual Media
  • 2024 : 📑 Efficient 3D Position Estimation in Badminton Scene appeared at ICASSP 2024.
  • 2024 : 📑 AMD appeared at AAAI 2024.
  • 2024 : 📑 MCM appeared at IJCAI 2024.
  • 2023 : 📑 REMAST was published in IEEE Transactions on Affective Computing.
  • 2023 : 📑 EnchantDance was published in IEEE Transactions on Multimedia.

📝 Publications

🎬 Video Generation and Talking Avatar

ALIVE 2026 ALIVE lifelike audio-video generation overview

ALIVE: Animate Your World with Lifelike Audio-Video Generation

Y. Guo, Q. Gan, Y. Zhang, J. Liu, Y. Hu, P. Xie, D. Qian, Y. Zhang, R. Li, Y. Zhang, R. Lu, X. Mei, B. Han, X. Yin, B. Peng, Z. Yuan

Technical Report (2026)

ALIVE presents a unified framework for lifelike audio-video generation and reference-based animation.

Project | Paper | Code

🕺 Human Motion Generation

AAAI 2024 AMD autoregressive motion diffusion framework overview

AMD: Autoregressive Motion Diffusion

Bo Han, H. Peng, M. Dong, Y. Ren, Y. Shen, C. Xu

Proceedings of the AAAI Conference on Artificial Intelligence (2024, CCF-A)

AMD generates long and complex human motions by combining autoregressive modeling with motion diffusion.

Paper | Code

arXiv 2026 PRISM motion generation tasks and results

PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

Z. Ling, Q. Shuai, T. Zhang, S. Li, Bo Han, C. Zou

arXiv preprint (2026)

PRISM targets streaming human motion generation with a per-joint latent decomposition design.

Paper | Code

ECCV 2026 VersatileMotion multimodal motion synthesis and comprehension tasks

VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension

Z. Ling*, Bo Han*, S. Li, J. Cheng, H. Shen, C. Zou

European Conference on Computer Vision (ECCV 2026)

VersatileMotion unifies motion synthesis and motion comprehension in one framework.

Demo | Paper | Code

IJCAI 2024 MCM multi-condition motion synthesis framework

MCM: Multi-condition Motion Synthesis Framework for Multi-scenario

Z. Ling*, Bo Han*, Y. Wong, M. Kangkanhalli, W. Geng

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (2024, CCF-A)

MCM studies multi-condition motion synthesis for multiple motion generation scenarios.

Demo | Paper | Code

🎵 Music and Dance Generation

CVMJ 2024 Dance2MIDI dance-driven multi-instrument music generation overview

Dance2MIDI: Dance-driven Multi-instruments Music Generation

Bo Han, Y. Li, Y. Shen, Y. Ren, F. Han

Computational Visual Media (2024, CCF-B)

Dance2MIDI studies dance-driven generation of multi-instrument MIDI music and introduces the D2MIDI dance-video/MIDI paired dataset.

Project | Paper | Code | Dataset

TAFFC 2023 REMAST real-time emotion-based music arrangement workflow

REMAST: Real-time Emotion-based Music Arrangement with Soft Transition

Z. Wang, L. Ma, C. Zhang, Bo Han, Y. Xu, Y. Wang, X. Chen, H. Hong, W. Liu, X. Wu, K. Zhang

IEEE Transactions on Affective Computing (2023)

REMAST focuses on real-time music arrangement driven by emotion conditions with soft transitions.

Paper | Code

TMM 2023 EnchantDance generated Latin dance sequence

EnchantDance: Unveiling the Potential of Music-Driven Dance Movement

Bo Han, T. Zhang, Z. Ling, Y. Ren, X. Yin, F. Han

IEEE Transactions on Multimedia (2023, CCF-A)

EnchantDance investigates expressive dance movement generation conditioned on music.

Project | Paper | Code

🧊 Vision and 3D Generation

ICASSP 2024 Illustration of dual-view 3D position estimation in a badminton scene

Efficient 3D Position Estimation in Badminton Scene

Bo Han, Liangjian Han

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)

A dual-view framework for efficient 3D estimation of badminton players and shuttlecock positions using 2D keypoints and epipolar geometry.

Paper | Session

ICIP 2023 SketchFFusion sketch-guided image editing framework

Sketchffusion: Sketch-guided Image Editing with Diffusion Model

W. Mao, Bo Han, Z. Wang

IEEE International Conference on Image Processing (ICIP 2023)

Sketchffusion uses sketch guidance to control image editing with diffusion models.

Paper | Session

🎖 Honors and Awards

Selected honors and awards that have encouraged my academic path.

  • 2024    AAAI Scholarship
  • 2024    Outstanding Graduate of Zhejiang University
  • 2023    China Scholarship Council Scholarship (CSC Scholarship)
  • 2023    Outstanding Graduate Student of Zhejiang University
  • 2018    National Scholarship (Top 1% among all undergraduates)
  • 2017-2018    MCM/ICM Honorable Mention, Mathematical Contest in Modeling / Interdisciplinary Contest in Modeling