Research
I'm interested in I'll be delving into the captivating realm of developing data-driven approaches to accelerate systems (ML for Systems) and, conversely, designing high performance systems that accelerate complex machine learning workloads (Systems for ML). Representative papers are highlighted.
|
|
Building Interpretable Predictive Models with Context-aware Evolutionary Learning
Binh Tran,
Chamika Sudusinghe,
Su Nguyen,
Damminda Alahakoon
Applied Soft Computing, 2023 (Vol. 132)
project page
/
video
/
arXiv
Combining mip-NeRF 360 and grid-based models like Instant NGP lets us reduce error rates by 8%–77% and accelerate training by 24x.
|
|
Eavesdropping Attack Detection using Machine Learning in Network-on-Chip Architectures
Amit Raj, Srinivas Kaza, Ben Poole, Michael Niemeyer, Nataniel Ruiz,
Ben Mildenhall, Shiran Zada, Kfir Aberman, Michael Rubinstein,
Jonathan T. Barron, Yuanzhen Li, Varun Jampani
ICCV, 2023
project page /
arXiv
Combining DreamBooth (personalized text-to-image) and DreamFusion (text-to-3D) yields high-quality, subject-specific 3D assets with text-driven modifications
|
|
Denial-of-Service Attack Detection using Machine Learning in Network-on-Chip Architectures
Lior Yariv*,
Peter Hedman*,
Christian Reiser,
Dor Verbin,
Pratul Srinivasan,
Richard Szeliski,
Jonathan T. Barron,
Ben Mildenhall
SIGGRAPH, 2023
project page
/
video
/
arXiv
We use SDFs to bake a NeRF-like model into a high quality mesh and do real-time view synthesis.
|
|
Hardware-Assisted Malware Detection using Machine Learning
Christian Reiser,
Richard Szeliski,
Dor Verbin,
Pratul Srinivasan,
Ben Mildenhall,
Andreas Geiger,
Jonathan T. Barron,
Peter Hedman
SIGGRAPH, 2023
project page
/
video
/
arXiv
We use volumetric rendering with a sparse 3D feature grid and 2D feature planes to do real-time view synthesis.
|
|
Network-on-Chip Attack Detection using Machine Learning
Dor Verbin,
Ben Mildenhall,
Peter Hedman,
Jonathan T. Barron,
Todd Zickler,
Pratul Srinivasan
arXiv, 2023
project page
/
video
/
arXiv
Shadows cast by unobserved occluders provide a high-frequency cue for recovering illumination and materials.
|
|