Scholar
Akash Pandey
Google Scholar ID: lIsyJTsAAAAJ
Northwestern University
Citations & Impact
Citations
156
H-index
7
i10-index
7
Publications
14
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- 1. Paper titled 'COLOR: A compositional linear operation-based representation of protein sequences for identification of monomer contributions to properties' accepted at MLGenX workshop in ICLR 2025
- 2. Submitted a paper on surface-EMG based silent-speech recognition using LLMs to ACL
- 3. Developed a novel eXplainable AI (XAI) method, named COLOR, which is now online on arXiv
- 4. Published academic research in Nature Communications Materials, ACS JCIM, ICLR’25 MLGenX workshop, and Cell Press Patterns
- 5. Published work in ACL’25, ICASSP’23, ACM Multimedia’23, and ACM IASA’22
Research Experience
- 1. Internship at Capital One, contributing to the development of recommendation systems
- 2. Full-time position at Rolls Royce, applying numerical optimization techniques for aero-engine structural analysis
- 3. Guiding Julia Levenshteyn to develop metrics to quantify explainability in computational biology
- 4. Guided Xiaoyuan Zhang to develop a Llama (2 and 3) based deep-learning model to predict text from silent EMG signals on a closed vocabulary
- 5. Guided Yueyuan Sui for the ACM MM 2023 challenge for human emotion prediction task
Education
- 1. PhD Candidate in Mechanical Engineering at Northwestern University, co-advised by Dr. Sinan Keten and Dr. Wei Chen
- 2. Master's by research in Applied Mechanics at Indian Institute of Technology (IIT) Madras, specializing in solid mechanics
- 3. Bachelor of Engineering in Automobile Engineering from Madras Institute of Technology, Anna University
Background
- Research interests include explainable deep learning models for scientific discovery, particularly in computational biology, time-series analysis, and recommendation systems. Skilled in Transformer architectures, attribution methods, and protein sequence modeling.
Miscellany
- Enjoys developing deep learning models for other sequential data such as audio, biosignals, and EMG
