Researcher in Generative World Modeling. Former Googler. NYU PhD.
Crepe. Character-level Convolutional Networks for Text Classification
848glyph. Which Encoding is the Best for Text Classification in Chinese, English, Japanese and Korean?
175tunnel. Data Driven Framework for Distributed Computing in Torch 7
24BigData. Collalboration Hub for the NYU's Big Data: Large Scale Machine Learning course
8XSVM. Kernel SVM in Torch 7
7GalaxyZoo. Code use for Galaxy Zoo competition on kaggle
7xjax. Simple framework for neural networks using Jax
6XBoost. eXetremely fast ada-Boost library
3old-hugo-website. Personal Website
2fastText. Library for fast text representation and classification.
1openplayground. An LLM playground you can run on your laptop
1tokenizers. 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
1lua-evdev. Lua module for reading Linux input events from /dev/input/eventXX nodes
1nn. Lua
1