currently a student at uc san diego studying computer science. i'm broadly interested in advancing
for the physical world.
my work spans from pretraining and model architectures to efficient inference and post-training paradigms.
most of my time right now is spent working with the
and
nvidia research,
while also contributing to
.
at
hao ai lab,
i'm working on understanding how video and world models learn causal dynamics and physical principles.
fastvideo
is an open-source framework for accelerating large-scale video generation through efficient post-training, distillation, and serving.
previously, i've interned with the autopilot team at
and the
pytorch
acceleration team at
.
at
tesla ai,
i worked on sota 3d foundation models, gpu kernels, and model training performance for fsd and optimus.
at
meta,
i helped build out the runtime software stack for next-generation training and inference chips to accelerate pytorch ops, powering recsys and ads models at scale.
