Saksham Bassi

I am a Research Engineer at NYU where I work with Kyunghyun Cho, He He and Claudio Silva.

I completed my MS in Computer Science at Courant Institute of Mathematical Sciences. During my MS, I worked at CILVR lab on evaluating cross lingual transfer of Large Language Models (LLMs) with Duygu Ataman and Kyunghyun Cho.

I spent summer of 2022 with Amazon Care to build a payment failure notification system to avoid unsuccessful payments. Prior to my masters, I was Data Scientist II at Glance, InMobi where I worked in the Personalisation team to enhance exploration of social media feed using Representation Learning models. Prior to that, I spent time at HSBC as a Software Engineer, where I built monitoring architecture and improved backend of financial applications.

In my past life, I have worked on deploying neural networks for classifying variable stars at IUCAA and in various time-series at Tata Institute of Fundamental Research.

Email  /  LinkedIn  /  Twitter  /  Github

profile photo
Interests

Apart from having interests in software engineering, my research interests lie in natural language understanding, model generalization, and machine learning. I have had a great time applying machine learning models in interdisciplinary fields like astronomy, medical imaging, finance, industrial IoT.

Visualizing Loss landscape of LLMs
Aayush Agrawal*, Saksham Bassi*, Rahul Sankar*
NYU CDS - NLP with Representation Learning course project

Visualizing two types of LLMs using their loss landscapes

Learning high-dimensional causal effect
Aayush Agrawal*, Saksham Bassi*
arXiv cs.LG

Tried hands on Causal Inference during Machine Learning course with Prof. Rajesh Ranganath.

Learning to classify Variable Stars Light Curves using Long Short Term Memory Network
Saksham Bassi*, Kaushal Sharma*, Atharva Gomekar
Frontiers in Astronomy and Space Sciences

One dimensional hybrid model of convolutional network and LSTM to classify variable star classes.

A learning algorithm for time-series based on statistical features
Saksham Bassi*, Atharva Gomekar*, A. S. Vasudeva Murthy
International Journal of Advances in Engineering Sciences and Applied Mathematics

Machine learning technique for time series which combines statistical features and neural networks to model, factorize and reconstruct data.

Change in structural patterns in the time series of Onion prices in India
Saksham Bassi*, Atharva Gomekar*, A. S. Vasudeva Murthy
In submission

Analyzing the structural patterns in time-series of Onion retail prices using various mathematical techniques to conclude about the patterns and periodicity.

A CNN approach to precision agriculture: An exploratory study
Atharva Gomekar*, Saksham Bassi*, A. S. Vasudeva Murthy
Project report, 2019  

Identifying diseases in farm fields using computer vision techniques on drone images. Transfer learning of pre-trained Convolutional Neural Networks and unsupervised segmentation as a pre-processing for training neural networks from scratch.

Deep Learning Diagnosis of pigmented Skin Lesions
Saksham Bassi*, Atharva Gomekar*
ICCCNT, 2019  [Link]

Convolutional Neural Networks to predict the kind of skin cancer using transfer learning and parallel networks





Source