I am a final-year student at BITS Pilani, K.K. Birla Goa Campus. I am currently working as a research intern at Serre Lab, Brown University and at the Chair of HPSN, Technische Universität Dresden . I am the President of the Society for Artificial Intelligence and Deep Learning. As a part of SAiDL, I am involved in different projects, research discussion sessions, conducting and teaching for student run courses, etc.
M.S. in Machine Learning, 2025
Carnegie Mellon University
B.E. in Electronics and Communication, 2024
[CGPA : 9.36]
BITS-Pilani, K.K. Birla Goa Campus
|
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre ICML 2023 : Oral & Poster arXiv We, analyse diffusion models and other generative models comparing their generation ability to humans by adapting the 'diversity vs. recognizability' scoring framework from Boutin et al, 2022 as well as comapre human category diagnostic features against those derived from diffusion models. |
|
Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference
Rishav Mukherji, Mark Schöne, Khaleelulla Khan Nazeer, Christian Mayr, Anand Subramoney MNLCP @ NeurIPS2023 : Poster arXiv We demonstrate that activity sparsity can compose multiplicatively with parameter sparsity in a recurrent neural network model based on the GRU that is designed to be activity sparse. |
Workshop, BITS Goa, Center For Technical Education, 2021
The course intends to help students with no experience in machine learning take their first steps in the field. We will start off with the basic Machine learning theory and look into essential tools needed for ML; libraries like numpy and pandas. Then we will proceed to teach the students about various machine learning algorithms, the maths behind it. With the help of scikit learn, the students will learn how to implement various models as well.
Course, BITS Goa, Center For Technical Education, 2022
This is an introductory course to natural language processing. We will cover a wide range of topics ranging from Spam, Sentiment classification to Machine Translation and Text Generation.
Built supervised (ResNet) , semi-supervised (Vanilla CNN with pseudo labelling) and unsupervised (SimCLR) models to carry out classification on STL-10 dataset and compared their functionality and effectiveness based on various parameters.
Developing models for carrying out Code Search and Duplicate Detection
on C/C++, Pyhton and Java source code.
Trained a BiLSTM Classifier on SNLI dataset to carry out inference and then analysed the model by carrying out probing based on POS tags.
Building algorithms capable of achieving performance comparable to the existing state-of-the-art TTC algorithms that use only monocular RGB videos as an input, at a computational budget
A PyTorch library which packages implementations of different kinds of ViTs and methods to visualize their attention maps, and provides an easy-to-use API.
Setting up a LoRaWAN based IoT network for emergency messaging system and
then using various ML/DL techniques to optimise the network and utilise it for wider purposes.
