Publications
-
QuIRK: Quantum-Inspired Re-uploading KAN Pre-Print
Sharma, Vinayak and Padhy, Ashish and Karanjkar, Vijay Jagdish and Behera, Sourav and Sen, Lord and Mukherjee, Shyamapada and Shrivastava, Aviral ; 2025
Quantum Machine Learning KANs
@misc{sharma2025quirkquantuminspiredreuploadingkan, title = {QuIRK: Quantum-Inspired Re-uploading KAN}, author = {Sharma, Vinayak and Padhy, Ashish and Karanjkar, Vijay Jagdish and Behera, Sourav and Sen, Lord and Mukherjee, Shyamapada and Shrivastava, Aviral}, year = {2025}, eprint = {2510.08650}, archiveprefix = {arXiv}, primaryclass = {quant-ph}, tag = {Quantum Machine Learning, KANs}, weblink = {https://mpslab-asu.github.io/QuIRK-PaperPage/}, url = {https://arxiv.org/abs/2510.08650}, preprint = {true} } -
LUCI: Lightweight UI Command Interface
Lagudu, Guna and Sharma, Vinayak and Shrivastava, Aviral ; 2025
Machine Learning LLM Agents UI Automation
@inproceedings{LUCI2025, author = {Lagudu, Guna and Sharma, Vinayak and Shrivastava, Aviral}, title = {LUCI: Lightweight UI Command Interface}, year = {2025}, isbn = {9798400719219}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, weblink = {https://mpslab-asu.github.io/LUCI-Page/}, url = {https://doi.org/10.1145/3735452.3735536}, doi = {10.1145/3735452.3735536}, booktitle = {Proceedings of the 26th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems}, pages = {182-191}, numpages = {10}, keywords = {Embedded Systems, LLM, System Automation}, location = {Seoul, Republic of Korea}, tag = {Machine Learning, LLM Agents, UI Automation}, series = {LCTES '25} } -
Primer on Data in Quantum Machine Learning
Shrivastava, Aviral and Sharma, Vinayak ; 2024
Quantum Machine Learning
@inproceedings{QuantumPrimer2024, author = {Shrivastava, Aviral and Sharma, Vinayak}, booktitle = {2024 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems (CASES)}, title = {Primer on Data in Quantum Machine Learning}, year = {2024}, volume = {}, number = {}, pages = {19-20}, tag = {Quantum Machine Learning}, keywords = {Performance evaluation;Quantum system;Machine learning algorithms;Quantum algorithm;Embedded systems;Computer aided software engineering;Machine learning;Computer architecture;Quantum state;Machine Learning;Quantum Information;Quantum Computing}, doi = {10.1109/CASES60062.2024.00010} } -
Quantum Polar Metric Learning: Efficient Classically Learned Quantum Embeddings Pre-Print
Sharma, Vinayak and Shrivastava, Aviral ; 2023
Quantum Machine Learning Metric Learning Representation Learning
@misc{sharma2023quantum, title = {Quantum Polar Metric Learning: Efficient Classically Learned Quantum Embeddings}, author = {Sharma, Vinayak and Shrivastava, Aviral}, year = {2023}, eprint = {2312.01655}, archiveprefix = {arXiv}, primaryclass = {quant-ph}, url = {https://arxiv.org/abs/2312.01655}, weblink = {https://mpslab-asu.github.io/QPMeL/}, tag = {Quantum Machine Learning, Metric Learning, Representation Learning}, preprint = {true} }
Projects
Face De-Identification
Scalable privacy preserving face de-identification
A scalable approach to preserving the privacy of bystanders in social media posts
- Entirely ‘edge’ system tested on low end android phones-
- Client side nature makes it scalable as no server compute required for new nodes,
- Edge compute improves privacy as unfiltered data never leaves the device
- Aesthetics are preserved via custom filter implementation based on human tendecies
QML-Tutorials
Set of tutorials to learn teach Quantum Machine Learning
A set of tutorials in PennyLane to teach Quantum Machine Learning convering:
- Toy dataset generation using random quantum circuits
- Basic Variational or Explicit Models
- Data ReUploading Models
- Quantum Kernel Classifiers or Implicit Models
ARCNN-keras
TF-keras implementation of ARCNN which removes JPEG compression artifacts
A tf-keras implementation of ARCNN mentioned in :
- Implemented ARCNN in tf.keras for easy of use
- Created a novel “lite” version using dilated convolutions and reducing the number of parameters to half of that of Faster ARCNN (64k -> 32k)
vinayak19th.github.io
The code repo for this website and instructions
Website hosting my resume and profile. Notable Features include:
- System persistent dark mode (Remembers your preference via cookies)
- Live Github based Statistcs
- Profie Statistics on the about page
- Project statistics per repository in the project page
- Reactive design for mobile friendly operation
- Tabbed Page for certifications for easy of reading and management
- Header section with live links such as :
- Direct whatsapp message
- Medium Profile
- Stack Overflow
- etc
- Modular self generating based on yml datasheets
LOW-RESOURCE ASR
A project based on the BABEL Dataset from the US government
- An End-to-End Framework for performing automatic speech recognition on low-resource languages such as
Urdu and Pashto
- Created the framework based on ESPnet.
Quantum Machine Learning
Implementations of code for the University of Toronto QML course
- Implementing QML algorithms from the University of Toronto Course
- Implemented in IBM Qiskit
PennyLane-Keras-Layer
Keras 3 Wrapper for PennyLane
- Find the package on:
- Keras 3 PennyLane wrapper with QNode interface automatically selected based on the keras backend
- Addded optimizations for JAX with
jax.compile - Support of saving and loading models
PennyLane-Keras3
Demo showing how to use PennyLane with Keras 3 with full multi-backend support (TensorFlow, JAX, PyTorch).
- Demo for Data-ReUploading models.
- Training loop tested on all 3 backends (Tensorflow, Keras, JAX)