Name: Jacob Kahn
Type: User
Company: Facebook AI Research
Bio: AI Research at FAIR, Meta AI (@facebookresearch), CS Faculty at @upenn. Formerly ran @pennapps.
Twitter: jacob_d_kahn
Location: New York | San Francisco
Blog: https://jacobkahn.me
Jacob Kahn's Projects
ArrayFire: a general purpose GPU library.
:rocket: Futuristic JavaScript test runner
Example pybind11 module built with a CMake-based build system
Conan for NVIDIA NCCL
My dotfiles.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Transformer related optimization, including BERT, GPT
A C++ standalone library for machine learning
Fast lattice reduction
Googletest - Google Testing and Mocking Framework
Server repo for Greylock things
Automatic differentiation with weighted finite-state transducers.
flashlight tap
Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2
KenLM: Faster and Smaller Language Model Queries
dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.
A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use
A Unity framework for multiplayer AR applications
Computer vision and data transmission infrastructure powering a MultiplayAR system
Basic NodeJS/Express version of a data transmission backend for a MultiplayAR system
Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
oneAPI Deep Neural Network Library (oneDNN)
The new PennApps Sponsor Portal – sponsor.pennapps.com
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
Using Q-learning to better navigate orderbooks.
C++ implementation of RSocket