Steve Lu's repositories
SRU-tensorflow
Training RNNs as fast as CNNs. An unofficial tensorflow implementation.
NTG-Papers
Paper List for (Unconditional) Neural Text Generation
py-stdio-ipc
Python IPC based on stdin / stdout
ACM-2015-AI-Server
Programming Fall 2015 Final Project AI Server
ACM_Website_2014_Develop
ACM_Website_2014_Develop
Back-N-Forth
Code base for the Back-N-Forth algorithm
CoT-pytorch
Official Implementation of the Cooperative Training algorithm
CS263AblatingRoBERTa
Ablation Study of the roles of architecture/weights of a Pretrained Encoder on Disaster Tweets dataset.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
desire2020.github.io
Personal page of Sidi ``Steve'' Lu.
image_captioning
Tensorflow implementation of "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"
NADO-LCG
NeurAlly-Decomposed Oracles
Pencil
A simple compiler for a mid-level programming language Pencil. Pencil is designed to be a superset of the Pen language, however not a pure functional programming language for it has to support some order-oriented programming patterns to fully satisfy the requirements of the development of project SuiX.
pytorch_memory_efficient_attention_with_learnable_bias
Implements Memory Efficient Attention in plain pytorch. Added support for (learnable!) biases.
SeqGAN-bench
SeqGAN with a more friendly interface.