sungjinl's repositories
agile
Official implementation of "Know Your Action Set: Learning Action Relations for Reinforcement Learning", Jain et al., ICLR 2022.
brain_agent
Brain Agent for Large-Scale and Multi-Task Agent Learning
captum
Model interpretability and understanding for PyTorch
COBS
OPE Tools based on Empirical Study of Off Policy Policy Estimation paper.
CommaQA
Code and Dataset for Learning to Solve Complex Tasks by Talking to Agents
d3rlpy
An offline deep reinforcement learning library
DeepDPM
"DeepDPM: Deep Clustering With An Unknown Number of Clusters" [CVPR 2022]
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
dialogue-meaning-representation
Data and code for the paper "Dialogue Meaning Representation for Task-Oriented Dialogue Systems".
dialogue-reinforce
Training chatbot models with reinforcement learning in ParlAI.
dowhy
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
ds2
Code for DS2 paper
industrialbenchmark
Industrial Benchmark
language
Shared repository for open-sourced projects from the Google AI Language team.
learning-scaffold
This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"
Megatron-LM
Ongoing research training transformer models at scale
MOML
Source Code of "Multi-Objective Meta Learning" [NeurIPS 2021]
naturalcc
NaturalCC: An Open-Source Toolkit for Code Intelligence
neural_chat
Code to support training, evaluating and interacting neural network dialog models, and training them with reinforcement learning. Code to deploy a web server which hosts the models live online is available at: https://github.com/asmadotgh/neural_chat_web
NLIWOD
Collection of tools, utilities, datasets and approaches towards realising natural language interfaces for the Web of Data.
OpenCSR
Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)
ReAgent
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
t-few
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
task_oriented_dialogue_as_dataflow_synthesis
Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).
Tk-Instruct
Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.
trans-encoder
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
unas
Official implementation of "UNAS: Differentiable Architecture Search Meets Reinforcement Learning", CVPR 2020 Oral