Personal blog with Jupyter notebooks

Neural network compression with SVD

Reimagining the newly constructed Hillhouse Avenue of Yale University

Graph neural ordinary differential equations

Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech

KoCLIP: Korean port of OpenAI CLIP, in Flax

A neural approach to malware detection in portable executables

A toolkit for identifying pretrained language models from potentially AI-generated text

Ensembling Hugging Face transformers made easy

N-gram keyword extraction using spaCy and pretrained language models

Transfer learning pretrained vision transformers for breast histopathology

PyTorch implementation of Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

PyTorch implementation of Rethinking Positional Encoding in Language Pre-training

PyTorch implementation of Pay Attention to MLPs

PyTorch implementation of Lessons on Parameter Sharing across Layers in Transformers

PyTorch implementation of FNet: Mixing Tokens with Fourier transforms

PyTorch implementation of RealFormer: Transformer Likes Residual Attention

PyTorch implementation of MLP-Mixer: An all-MLP Architecture for Vision

PyTorch implementation of ResMLP: Feedforward networks for image classification with data-efficient training