architsharma97
Currently PhD student at Stanford @stanford-iris-lab. Previously, AI Resident at @google-research, @mila-iqia, @IITKanpur
Pinned Repositories
architsharma97.github.io
Personal Website based on "Goa" for Hugo
CV
Personal CV, based on Alessandro Plasmati's.
dpo-rlaif
earl_benchmark
EARL: Environment for Autonomous Reinforcement Learning
medal
Code to reproduce results for MEDAL in PyTorch. Also contains code for running SAC and FBRL.
self-improving-robots
Website for Self-Improving Robots.
VideoSummarization
Course Project for CS771: Machine Learning
VisualDialog
The repository contains Theano implementations for Visual Dialog Models (http://visualdialog.org/). In particular, the Late Fusion and Memory Network models have been implemented.
VisualQA
A model for Visual Question Answering. Extracts image features using the vgg16 architecture. Extracts language features using LSTM. Outputs from both are combined using a fully connected MLP, outputs of which belong to pre-chosen set of most probable answers.
dads
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
architsharma97's Repositories
architsharma97/dpo-rlaif
architsharma97/earl_benchmark
EARL: Environment for Autonomous Reinforcement Learning
architsharma97/VideoSummarization
Course Project for CS771: Machine Learning
architsharma97/medal
Code to reproduce results for MEDAL in PyTorch. Also contains code for running SAC and FBRL.
architsharma97/CV
Personal CV, based on Alessandro Plasmati's.
architsharma97/VisualDialog
The repository contains Theano implementations for Visual Dialog Models (http://visualdialog.org/). In particular, the Late Fusion and Memory Network models have been implemented.
architsharma97/VisualQA
A model for Visual Question Answering. Extracts image features using the vgg16 architecture. Extracts language features using LSTM. Outputs from both are combined using a fully connected MLP, outputs of which belong to pre-chosen set of most probable answers.
architsharma97/architsharma97.github.io
Personal Website based on "Goa" for Hugo
architsharma97/ImageToolbox
A simple toolbox which does Red-Eye Reduction and Segmentation based Selective Blurring of Images. Has a simple Tkinter based GUI, which accepts images and performs the selected functions.
architsharma97/InstanceRetrieval
Assignment for CS698O: Visual Recognition
architsharma97/mbsvme
Mixture of Bayesian SVM Experts
architsharma97/MNIST
Tests convergence of various estimators. In particular, PD and SF/REINFORCE are tested for gaussian and bernoulli latent variables and Synthetic gradients are tested in MNIST Classification (DNI).
architsharma97/Privacy_SPMD
Privacy analsyis in DSRC: Data taken from Ann Arbor, Michigan. Conclusively shows that switching IDs randomly will not preserve user privacy is BSMs are transmitted at 10 Hz. Also shows lack of privacy if IDs are changed universally. Other protocols under test, where IDs are only transmitted when driving through an intersection.
architsharma97/self-improving-robots
Website for Self-Improving Robots.
architsharma97/LocationTagger
An android application which takes input from the user about his/her method of commute. There are four options available: Walk, Bus, Car and Bike. Currently pushes data to server within Texas A&M.
architsharma97/opencv
Open Source Computer Vision Library
architsharma97/self-improving-robot-sail-blog
SAIL blog entry for Self-Improving Robots