Name: Premith Kumar Chilukuri
Type: User
Company: ABB, Virginia tech
Bio: Machine Learning Engineer and AI Researcher with current and previous work-experiences at ABB, Virginia Tech, Samsung R&D Institute, Supervue Ai, and Zebi Data.
Location: Raleigh, NC, 27606
Blog: https://premithchilukuri.com/
Hi š, I'm Premith Kumar Chilukuri
Machine Learning Engineer and AI Researcher
š Iām currently working on 3D Object generation using Voxel DDPMs, Multi-Modal LLMs (RAG, finetuning, & Quantization), and Distributed ML Systems
šÆ Iām looking to collaborate on NeRF infused Diffusion Models for single view 3D object generation
šØāš» All of my projects are available at https://github.com/chpk
š« How to reach me [email protected]
š Know about my experiences https://premithchilukuri.com/#work-ex
Premith Kumar Chilukuri's Projects
A cutting-edge portfolio web page utilizing vanilla JavaScript.
INFORMS QSR 2024 Challenge Website using streamlit and MongoDB
Repo for CS 5704 project.
Making easy to run LLMs locally on simple machines using Model sharding, Quantization, layer wise inferencing techniques etc.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
An interactive demo based on Segment-Anything for style transfer which enables different content regions apply different styles.
Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch