dido1998

Recurrent-Independent-Mechanisms

Implementation of the paper Recurrent Independent Mechanisms (https://arxiv.org/pdf/1909.10893.pdf)

CausalMBRL

Official data and code for our paper Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

coqa-bert-baselines

BERT baselines for extractive question answering on coqa (https://stanfordnlp.github.io/coqa/)

autonlp

NLP library for tasks like generation,inference etc

h-detach

Code for h-detach: Modifying the LSTM Gradient Towards Better Optimization - https://arxiv.org/abs/1810.03023

habitat-api

A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.

iclr-reproducibility-template

latex code for the paper

PCNO

Parallel Computation for Numerical Operations

chainer

As a part of my GSoC project I have contributed many routines to ChainerX. A more detailed description of my contributions is available in the README.

pruning

This repo is demonstrates pruning in tensorflow

academic-kickstart

academic-kickstart-1

academic-kickstart-2

Personal website code

academic-kickstart-3

c-swm-1

Contrastive Learning of Structured World Models

cruxeval

google-research

Google Research

habitat-sim

A flexible, high-performance 3D simulator for Embodied AI research.

hugo-academic

The website designer for Hugo. Build and deploy a beautiful website in minutes :rocket:

iclr_2019

ICLR Reproducibility Challenge 2019

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

Matterport3DSimulator

AI Research Platform for Reinforcement Learning from Real Panoramic Images.

MidasTask

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Pascal-Loop-Parser

PublicTransport

shadesmar

Fast C++ IPC using shared memory (with msgpack)

Shapes-Envionment

Gym implementation of the shape environment described in http://proceedings.mlr.press/v97/das19a/das19a.pdf

skill_discovery

slot-attention-smolensky