publications

Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor

Can Vision-Language Models Answer Face to Face Questions in the Real-World?

SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound

AirLetters: An Open Video Dataset of Characters Drawn in the Air

NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild

Beyond the Visible: Jointly Attending to Spectral and Spatial Dimensions with HSI-Diffusion for the FINCH Spacecraft

DiffuseRAW: End-to-End Generative RAW Image Processing for Low-Light Images

Astroformer: More Data Might Not be All You Need for Classification

CPPE-5: Medical Personal Protective Equipment Dataset

Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data

PyTorch Made Efficient for the Edge: WASI-NN

Orchestrating Machine Learning on Edge Devices with PyTorch and WebAssembly (Oral)