QasimWani

LeetHub

Automatically sync your leetcode solutions to your github account - top 5 trending GitHub repository

gct

Graphical Code Tracer (GCT): Visualize code at lightning speed

leetcode

Collection of LeetCode questions to ace the coding interview! - Created using LeetHub.

RL-Unity

Implementation of Deep Reinforcement Learning algorithms in the Unity game engine.

histogram_equalization

Robust Local Histogram Equalization written from scratch

ZOiRL

Zeroth-Order Implicit Reinforcement Learning. 🏆 Winner of 2021 CityLearn RL research competition!

Market_Analytics

Winner of VTHacks7. Best use of Machine Learning.

off-policy-evaluation

Approaching OPE as a regression problem using meta-learning.

IFMXFL

Influence Function for model explainability for federated learning

qasimwani.github.io

Crammer

Save that extra 5 minutes from Procrastination by automatically bundling images and converting it into word/PDF that's sent to your email with one click of a button.

QasimWani

CACTUS

CACTUS - Collection and Analysis of Cyber Technologies Under Security

DAML

Pseudocode Implementation of DAML, Domain Adaptive Dialog Generation via Meta Learning

EARL

Environment Aware Reinforcement Learning

facenet

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

finna

Largest Database for connecting driven developers and entrepreneurs

ReadMe

reads your history -- VT Hacks workshop demo

adaptive-median

Adaptive-median image filter in pure python - use with

advex_technical_interview_data

alls

Active learning under label shift.

cache-simulator

Simulate an LRU cache of different configurations

CityLearn

Official reinforcement learning environment for demand response and load shaping

cocp

Source code for the examples accompanying the paper "Learning convex optimization control policies."

COVID-CT

COVID-CT-Dataset: A CT Scan Dataset about COVID-19

deep-compression

Deep Denoising Compressive Autoencoder.

FreshDetect

Supply chain management platform to prevent food waste with IoT smart containers and Machine Learning - HackMIT 2019 🏆

PaLM-rlhf-pytorch-bugfix

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

robust_label_shift

Label Shift Domain Adaption

SMAAC

The official implementation of "Winning the L2RPN Challenge: Semi-Markov Afterstate Actor-Critic", ICLR 2021