I am a final-year M.S. student in the Department of Computer Science at
Brown University, advised by
George Konidaris,
Daniel Ritchie, and
Thomas Serre.
Previously, I have enriched my research experience at the National University of Singapore (NUS). I earned my B.S. in Computer Science from Fort Hays State University
(FHSU).
My research focuses on world models, generative modeling, and embodied intelligence, building systems that reason about
physical dynamics and interaction to support planning and decision-making.
I am grateful to be supported by the ONR and REPRISM MURI, and
the ANR-3IA Artificial and Natural Intelligence Toulouse
Institute grants.
“Vutha” is my surname, “Chealyfey” is my
given name, and “Lyfey” is the name I usually go by. On
a side note, my initials are “CV,” so I was destined
to do computer vision.
I am actively seeking for PhD opportunities during the 2026-27
admissions cycle.
News
May 26, 2026.
Thanks to
Thomas Serre
for sponsoring my summer research!
May 08, 2026.
Completed my second semester at Brown,
CSCI 2952N: Advanced Topics in Deep Learning
with Chen Sun, where I led a project on
Feature-Based Geodesic Interpolation with Diffusion and
Flow Models, and
CSCI 2951X: Reintegrating AI
with George Konidaris, where I worked on
Learning Improved Inverse Dynamics Models for Visual
Planning from Actionless Video.
April 20, 2026.Gave a talk at Brown's Visual Computing Seminar titled
Feature-Based Geodesic Interpolation with Diffusion and
Flow Models. Thanks to
Daniel Ritchie and
James Tompkin for
hosting me!
Sep 04, 2025.Started my Master of Science in Computer Science at Brown
University.
Publications
Feature-based Geodesic Interpolation for Diffusion and Flow
Models
Chealyfey Vutha, Zheyu Shi, Yuqiao Guan,
Arman Maesumi, Daniel Ritchie
Under Submission
We study interpolation in diffusion and flow models by
following feature-aware geodesic paths, which enables smoother
and more semantically consistent transitions between generated
images.