Selected Projects

Elastic-NeRF

nerf

elastic

wip

Making NeRFs even more compact and efficient using an elastic architecture (and no additional training cost)!

NAS-NeRF

nerf

nas

neurips workshop

We introduce a generative neural architecture search strategy that generates compact, scene-specialized NeRF architectures.

NV-Synth

synthetic data

neurips workshop

We introduce a large-scale synthetic food image dataset for nutrition estimation. NV-Synth contains 84,984 photorealistic meal images rendered from 7,082 dynamically plated 3D scenes.

DARLEI

RL

evolution

cvis

DARLEI combines evolutionary algorithms with parallelized reinforcement learning for efficiently training and evolving populations of UNIMAL agents.

TurboViT

vit

nas

neurips workshop

We explore the generation of fast vision transformer architecture designs via generative architecture search to achieve a strong balance between accuracy and architectural and computational efficiency.

Maple-Edge

edge-ml

latency prediction

cvpr workshop

We propose MAPLE-Edge, an edge-device oriented latency predictor where we train a regression network on architecture-latency pairs in conjunction with a hardware-runtime descriptor to effectively estimate inference latency on a diverse pool of edge devices.