profile photo

Karan Bania

 -  Updates  -  Experience  -  Projects  -  Contact  -  Alt. Contact  -  Phone  - 

I am an undergraduate student at BITS Pilani, Goa Campus where I'm pursuing Bachelor of Engineering in Computer Science. I am currently working under Prof. Ashwin Srinivasan & Prof. Sidong Liu at APPCAIR on developing a generalist AI for radiology reports.

My interests revolve around Graph Neural Networks, Multimodal Multitask Learning, Computer Vision and (some xD) Robotics. I am actively looking for research work related to GNNs, if you would like to collaborate please drop an email! I will be working at Rex Ying's lab at Yale University starting this October!

I am a member of SAiDL, Society for Artificial Intelligence and Deep Learning at BITS Goa; we try to inculcate a spirit of AI and DL in the university through open source projects and personalised courses. I am also a part of Project Kratos' autonomous subsystem, we build a working Mars Rover capable of Life Detection and autonomous travel and enter competitions regarding the same.

In my free time you'll probably find me reading up on theoretical computer science (sorry, not sorry). I am a pretty radical supporter of R&B and rap. Apart from this, I love to teach (just about anything) and am an active member of the institute's Table Tennis team.

Feel free to check out my CV , you can reach out to me at my email. Thanks!

 ~   |  Email  |  CV  |  GitHub  |  LinkedIn  |   ~ 

September '23

Will be starting remote work on GNNs at Yale!

August '23

Selected for a Reading Course on LLMs instructed by Prof. Lovekesh Vig from TCS Research!

August '23

Selected as a course instructor for the CTE course "Intro to ML/DL"!

August '23

Started at APPCAIR lab as a student researcher!

August '23

Selected as a teaching assistant for CS F214 - Logic in Computer Science.

July '23

Selected for IIITH's 7th Summer School on AI with focus on Computer Vision.

July '23

Selected for Neuromatch Summer School'23 in the Deep Learning Track.

June '23

Will be working as a ML intern at VoiceQube for summer 2023.

Research Assistant | Yale University
Upcoming October '23 - Present

Working on GNNs, Knowledge Graphs and LLMs under Prof. Rex Ying. My work involves implementing models in PyG and carrying out experiments on various datasets.

Undergraduate Researcher | APPCAIR & Macquarie University (Australia)
August '23 - Present

Building a generalist (multi-modal) AI for Chest X-rays, which can tutor, synthesize and correct radiology reports; as well as generate synthetic images according to a radiology report under Prof. Ashwin Srinivasan and Prof. Sidong Liu.

Member | SAiDL
July '23 - Present

My work is ubiquitous in the society, I am involved in taking courses, organizing our Annual Symposium, [eg. of 2021's event], as well as deciding topics for our SsOC (SAiDL Season of Code), [again eg. library from 2021]. One of the three people inducted from our batch.

ML Intern | VoiceQube
June '23 - August '23

Worked on an AI research project to incorporate explicit sentiment analysis into effective stock market trading solutions.

Kratos The Rover
August '23 - Present

Working on path planning algorithms (A*, Dijkstra, etc.), along with point clouds; also ran simulations on Gazebo.

Image Segmentation on arbitrary prompts using Open AI's CLIP

I tried out various loss functions for segmentation and various model depths. Increased the inference time processing speed by training a light-weight decoder. Basically reproduced the CLIPSeg Paper.

Reinforcement Learning as a Sequence Modelling Task

Read up on decision transformers and replaced them with other sequence models; LSTMs, GRUs and an Elman RNN and compared them to the original transformer. (The figure is a display of the results on LSTMs - Medium (offline data) - Normal (Rewards))

✨Zero Knowledge Proofs✨

a (un)popular video.

As of 10/09/23

My repository on cs224w's (Stanford Machine Learning with Graphs) assignment solutions is the only one with solutions to all problems (not just coding assignments)!


Your newest wallpaper xD

(Very) Amazing paper on GNNs!

(GSAT) - Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism
My Slides

Multi-task optimization 👌🏻

(BLIP) - Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Google just being Google

(Gshard) - Scaling Giant Models with Conditional Computation and Automatic Sharding
My Slides

New paradigm on GNN's applicability

(CrysXPP) - An Explainable Property Predictor for Crystalline Materials

This template is a modification to Jon Barron's website. Find the source code to my website here.