| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 28 Dec 2025 00:09:24 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69507534-9921"
expires: Mon, 29 Dec 2025 17:23:35 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 17AA:2C10E1:9249E5:A40CA7:6952B6BF
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 17:13:36 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210038-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767028416.870407,VS0,VE223
vary: Accept-Encoding
x-fastly-request-id: 726fc49878534a36d461dd6346c8787f073675e2
content-length: 6779
Tsai-Shien Chen
Captured at the stunning Santa Monica Beach, where I spent the summers of 2023 through 2025.
Biography
Welcome! I am a fourth-year Ph.D. candidate at UC Merced, advised by Prof. Ming-Hsuan Yang. I am also a research intern at Snap Creative Vision team, where I am privileged to work with Aliaksandr Siarohin, Sergey Tulyakov, Jun-Yan Zhu, and Kfir Aberman. Previously, I did my M.S. and B.S. at National Taiwan University.
My research centers on controllable and personalized image and video synthesis, aiming to enable more immersive and intuitive content creation.
NEW! Deeply honored to be awarded the 2025 Google PhD Fellowship.
NEW! Looking for research internship positions starting from 2026.
News
Dec 2025 NEW!
Dec 2025 NEW!
Omni-Attribute and AlcheMinT were released on arXiv.
Nov 2025 NEW!
LayerComposer and Canvas-to-Image were released on arXiv.
Oct 2025 NEW!
Awarded 2025 Google PhD Fellowship in Machine Perception.
July 2025
Granted two U.S. patents related to a video dataset and a video foundation model.
July 2025
Invited talk at Anuttacon on video datasets, foundation and application models.
Feb 2025
Video Alchemist was accepted to CVPR 2025.
June 2024
Awarded the Graduate Student Opportunity Program fellowship (full tuition).
Sep 2024
VIMI was accepted to EMNLP 2025 in the main conference track.
Feb 2024
Panda-70M was accepted to CVPR 2024.
Feb 2024
Snap Video was accepted to CVPR 2024 as a highlight presentation (2.8% acceptance rate).
May 2023
Joined the Snap Creative Vision team as a research intern.
Selected Projects
Check the full publication list in CV
AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation
arXiv preprint 2025
Canvas-to-Image: Compositional Image Generation with Multimodal Controls
Yusuf Dalva,
Guocheng Gordon Qian,
Maya Goldenberg,
Tsai-Shien Chen,
Kfir Aberman,
Sergey Tulyakov,
Pinar Yanardag,
Kuan-Chieh Jackson Wang
arXiv preprint 2025
LayerComposer: Multi-Human Personalized Generation via Layered Canvas
Guocheng Gordon Qian,
Ruihang Zhang,
Tsai-Shien Chen,
Yusuf Dalva,
Anujraaj Argo Goyal,
Willi Menapace,
Ivan Skorokhodov,
Meng Dong,
Arpit Sahni,
Daniil Ostashev,
Ju Hu,
Sergey Tulyakov,
Kuan-Chieh Jackson Wang
arXiv preprint 2025
Multi-subject Open-set Personalization in Video Generation
Tsai-Shien Chen,
Aliaksandr Siarohin,
Willi Menapace,
Yuwei Fang,
Kwot Sin Lee,
Ivan Skorokhodov,
Kfir Aberman,
Jun-Yan Zhu,
Ming-Hsuan Yang,
Sergey Tulyakov
CVPR 2025
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Tsai-Shien Chen,
Aliaksandr Siarohin,
Willi Menapace,
Ekaterina Deyneka,
Hsiang-wei Chao,
Byung Eun Jeon,
Yuwei Fang,
Hsin-Ying Lee,
Jian Ren,
Ming-Hsuan Yang,
Sergey Tulyakov
CVPR 2024
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
Willi Menapace,
Aliaksandr Siarohin,
Ivan Skorokhodov,
Ekaterina Deyneka,
Tsai-Shien Chen,
Anil Kag,
Yuwei Fang,
Aleksei Stoliar,
Elisa Ricci,
Jian Ren,
Sergey Tulyakov
CVPR 2024 [Highlight, 2.8% acceptance rate]
Motion-Conditioned Diffusion Model for Controllable Video Synthesis
arXiv preprint 2023
Incremental False Negative Detection for Contrastive Learning
ICLR 2022
Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network
ECCV 2020 [Oral, 2.1% acceptance rate]