Scholar
Jiaben Chen
Google Scholar ID: egMKh7MAAAAJ
University of Massachusetts, Amherst
Citations & Impact
Citations
419
H-index
10
i10-index
10
Publications
14
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- - TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation. NeurIPS, 2025
- - RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text. ICCV, 2025
- - SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation. CVPR, 2024
- - Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction. ECCV, 2024
- - RoboDreamer: Learning Compositional World Models for Robot Imagination. ICML, 2024
- - UniMuMo: Unified Text, Music and Motion Generation. AAAI, 2025
- - Revisiting Event-based Video Frame Interpolation. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024
Research Experience
- - Research intern at Meta Reality Labs working with Chengde Wan in 2025.
Education
- - Ph.D. in Computer Science at UMass Amherst, advised by Prof. Chuang Gan
- - Master's degree in Computer Science at CSE of University of California, San Diego, mentored by Prof. Xiaolong Wang
- - Bachelor's degree in Computer Science and Technology at SIST of ShanghaiTech University, worked as a research intern with Prof. Jianbo Shi at the University of Pennsylvania during junior and senior years.
Background
- Primary research interest: multi-modality learning and video synthesis.
Miscellany
- Contact: Email / Google Scholar / Github / Twitter / LinkedIn
