dhruvsrikanth Goto Github PK

followers: 27.0 following: 39.0 repos: 54.0 gists: 1.0

Name: Dhruv Srikanth

Type: User

Company: WecoAI

Bio: Researcher @WecoAI. Previous research at @autonlab @Center-for-Applied-AI. MS @uchicago-cs.

Twitter: DhruvSrikanth

Blog: https://dhruvsrikanth.github.io/

I'm a researcher at Weco AI, building LLM and VLM agents for code generation and problem solving. Previously I spent time at the Auton Lab at the Robotics Institute at CMU, where I worked on deep learning algorithms for vision, robotics and time-series. I also spend my free time working on AI safety, specifically alignment and fairness in computer vision. Prior to this, I worked on efficient deep learning for 2D-3D single-view reconstruction. In the past, I've spent some time doing applied machine learning and deep learning research at a few startups and large companies.

Apart from AI research, I enjoy high-performance computing and all the kernel/thread/cluster programming (debugging lol) that comes with it. I've made a few games, simulations, and systems.

I like to apply my research to healthcare, climate, industrial, and scientific problems. I am interested in AI and research at companies that take a practical engineering approach to innovation and impact.

Outside of research I enjoy being spending time outdoors by hiking, surfing and playing golf.

Open Source Contributions

Deep Learning
AutonFeat: A high-performance Python package for automatic and distributed time series feature extraction and selection
tsfresh: A time series feature extraction package
Denoising Diffusion Probabalistic Models (DDPMs)
2D-3D Single View Reconstruction
pynn (Deep Learning Framework with pure NumPy Computation)
VanillaGAN (Vanilla GAN experimentation library)
ConditionalGAN (Conditional GAN experimentation library)
DCGAN (DC GAN experimentation library)
PSNRGAN (Contrastive PSNR GAN experimentation library)
Monocular Depth Estimation
Neural Artistic Recreation (A CLI for Neural Style Transfer)

High-Performance Computing
CUDANN (Distributed Deep Learning Framework accelerated on NVIDIA GPUs)
FastConv (Multithreaded GPU CUDA kernels for Convolution)
Ray Tracing (using Monte-Carlo Algorithm on GPU Accelerators)
Advection Diffusion Simulation (Multithreaded, Shared Memory Parallelism, Distributed Memory Parallelism)
N Body Particle Simulation (Multithreaded, Shared Memory Parallelism, Distributed Memory Parallelism)
Distributed Poisson Solver (using Conjugate Gradient Optimization)
Image Editor via Convolutions (using Work Stealing and Work Balancing parallel schemes)
Sparse Linear Solver (using the Map Reduce parallelism scheme with Conjugate Gradient Optimization)
Image Editor via Convolutions (using Pipeline and BSP parallel schemes)
Twitter Application (using Producer-Consumer parallelism model)

Machine Learning
Boosting and Boostability (An understanding through Computational Learning Theory)
Financial Forecasting of TSLA (using sentiment analysis, feature engineering, and RNNs)

Computer Systems
GoLLUM - A GoLang Compiler
Unix Shell

Games
Climbing Mount Everest (A text-based adventure game)

Other
Useful Algorithms
Superconductor Regression (Kaggle Challenge)
Canvas Web Application
Blood Donations Database

Dhruv Srikanth's Projects

2d-3d-single-view-reconstruction

IEEE paper implementation of Single-View 2D-3D Reconstruction.

3d-r2n2

Single and Multi-view 2D-3D Reconstruction using Gated RNNs in an Autoencoder Network

advection-diffusion-simulation

In this repository, you will find a serial, shared-memory parallel, distributed-memory parallel and hybrid implementations of the advection-diffusion simulation.

algorithms

A collection of useful algorithms I am learning or have learnt and implemented to further develop my understanding!

basic-data-science

A short Data Science Project I took up for fun! This is a data analysis based on a dataset I created to predict the distribution of wealth within an economy as well as several characteristics of each class within society!

blood-donations-db

A blood donations database project.

boosting-theory

A collection of papers produced on the theory of boosting as applied to binary classification. Further extensions to the multi-class classification problem and necessary and sufficient conditions to ensure boostability i.e. weak learning conditions. Finally, an overview over boosting algorithms and models employed in industry.

climbingeverestgame

Climb the treacherous Mount Everest in this exciting text-based adventure game! A game through which you can experience a pure (Haskell) climb!

clrs

Consult the DeepMind clrs repository for the description.

communication-and-encryption-between-different-networks

A project a classmate and I undertook to better understand and develop end-to-end encryption between a client and server on a vulnerable network!

conditionalgan

Simulate experiments with the Conditional GAN architecture and training algorithm in PyTorch using this package.

conjugate-gradient-simulation

In this repository, you will find a serial, shared-memory parallel, distributed-memory parallel and hybrid implementations of the conjugate gradient optimization simulation. This is a sparse linear solver optimized using the second-order poisson equation.

cudann

A distributed implementation of a deep learning framework in CUDA.

dcgan

deep-learning

A variety of models implemented!

denoisingdiffusionprobabilisticmodels

An implementation of Denoising Diffusion Probabilistic Models (DDPMS) with experiments on different beta schedulers.

dhruvsrikanth

dhruvsrikanth.github.io

example-scripts

The official example scripts for the Numerai Data Science Tournament

fastconv

Distributed and serial implementations of the 2D Convolution operation in c++ and CUDA.

frozen-lake-q-learning

A reinforcement learning-based approach playing the frozen lake game from openai-gym.

gollum

A compiler for GoLite, a simple mix between Go and C/C++. The compiler uses LLVM for its IR representation and is designed for an ARM64 backend architecture.

learning-vim

Learning Vim from scratch!

lightning

Deep learning framework to train, deploy, and ship AI products Lightning fast.

mapreducesparsesolver

An Go native implementation of the Map Reduce parallel framework for a sparse linear solver utilizing conjugate gradient to solve the Poisson equation.

ml-templates

Templates for AI projects.

mlx

MLX: An array framework for Apple silicon

mlx-graphs

Graph Neural Network library made for Apple Silicon

model-pipelines

Model Pipelines for GNNs, VAEs, Neural Style Transfer, and other kinds of models!

monodepth

Monocular Depth Estimation via Transfer Learning using purely Tensorflow 2.0!

dhruvsrikanth Goto Github PK

Open Source Contributions

Dhruv Srikanth's Projects

Recommend Projects

Recommend Topics

Recommend Org