` Abhilash Neog

Abhilash Neog

I am a Ph.D. student at Virginia Tech where I am supervised by Prof. Anuj Karpatne. Currently, I work as a graduate research assistant at the Knowledge-guided Machine Learning Lab.

I received my Bachelors in Computer Science from BITS Pilani, India. During my undergraduate, I worked with Prof. Lavika Goel on soft computing algorithms for enhancing ML techniques. I also worked as a researcher at the ADAPT Lab advised by Prof. Navneet Goyal, and at CSIR CEERI advised by Dr. J.L. Raheja.

I have also spent some time in the industry - Kryptowire (Summer 2023), Oracle (2020-2022), VMware (Spring 2020), Samsung Research (Summer 2019)

Email  /  CV  /  Scholar  /  Twitter  /  Github  /  Linkedin

profile photo

Recent News

Research

My broad research interests include Foundation and Multimodal Models, LLMs for Time series, Model distillation and out-of-distribution generalization. Currently, my work is on robust time-series modeling, LLM alignment and pre-trained large models for time-series (foundation models). Some of the challenges I am trying to address are generalization across unseen data distributions, cross-frequency learning and knowledge transfer from simulation to real-world data.

Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images
K.S. Mehrab, M. Maruf, Arka Daw, Abhilash Neog, +13 authors.
CVPR 2025  
arXiv / Huggingface
We present Fish-Vista dataset of 80K fish images spanning 3000 different species supporting several challenging and biologically relevant tasks including species classification, trait identification, and trait segmentation
Masking the Gaps: An Imputation-Free Approach to Time Series Modeling with Missing Data
Abhilash Neog, Arka Daw, Sepideh Fatemi Khorasgani, Anuj Karpatne
Time Series in the Age of Large Models, NeurIPS 2024  
Paper
We propose a novel imputation-free approach of handling missing values in time series that can be trained in an end-to-end manner.
VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
M. Maruf, Arka Daw, K.S. Mehrab, H.B. Manogaran, Abhilash Neog, +17 authors.
NeurIPS 2024  
Paper / Huggingface
This work assesses state-of-the-art vision-language models (VLMs) using the VLM4Bio dataset for biologically relevant Q&A tasks on fishes, birds, and butterflies, exploring their capabilities and reasoning limitations without fine-tuning.
Modular Compositional Learning Improves 1D Hydrodynamic Lake Model Performance by Merging Process-Based Modeling With Deep Learning
R. Ladwig, A. Daw, E.A. Albright, C. Buelo, A. Karpatne, M.F. Meyer, A. Neog et al.
Journal of Advances in Modeling Earth Systems, 2024
Paper
Hybrid Knowledge-guided Machine Learning models using modular compositional learning (MCL) integrate deep learning into process-based frameworks, achieving superior accuracy in water temperature and hydrodynamics simulations compared to standalone models.
Hybrid Nature-inspired Optimization Techniques in Face Recognition
Lavika Goel, Abhilash Neog, Ashish Aman, Arshveer Kaur
Transactions on Computational Science XXXVI, 2020
Paper
We propose two hybrid nature-inspired optimization algorithms combining Gravitational Search Algorithm, Big-Bang Big-Crunch, and Stochastic Diffusion Search to enhance face recognition by optimizing PCA-derived Eigenfaces for SVM classifiers.

Projects

Can Large Vision Language Models Ground Fine-grained Attribute?
PDF
Developed a novel dual-scale attention framework for fine-grained attribute localization in Large Vision-Language Models (LVLMs), incorporating entropy-based head selection, maximally connected component filtering, and hierarchical constraints.
Evaluating Model Reasoning and Hallucinations in Medical LLMs
PDF / Code
Evaluated reasoning and hallucination patterns in open-source medical LLMs, analyzing their factual consistency and susceptibility to adversarial prompts, with insights for improving reliability in healthcare applications.
Convergence analysis of PINN for solving inverse PDEs
PDF / Code
Analyzed the convergence behavior of Physics-Informed Neural Networks (PINNs) for solving inverse PDE problems, demonstrating that adaptive loss weighting improves parameter estimation accuracy compared to sequential training.
Numeral Aware Language Generation
PDF / Code
Investigated the numerical reasoning capabilities of Large Language Models (LLMs) in numeral-aware headline generation, evaluating zero-shot, few-shot prompting, and fine-tuning approaches as part of the SemEval'24 NumEval challenge.
Understanding Universal Discriminative Quantum Neural Networks
PDF
Conducted an in-depth study on Quantum State Discrimination (QSD), analyzing strategies and challenges, with a focused discussion on the "Universal Discriminative Quantum Neural Networks" paper and its approach to quantum circuit training
Segmentation, Summarization and Classification of Electronic Theses and Dissertations (ETDs)
PDF
Developed an end-to-end ETD processing system for segmentation, summarization, and classification using deep learning and NLP models, improving retrieval and analysis efficiency.

Miscellaneous

Graduate Teaching Assistant, CS5805 Machine Learning, Spring 2024
Machine Learning Based Spend Classification
Akash Baviskar, K. Ramanathan, Abhilash Neog, Dipawesh Pawar, Karthik Bangalore Mani
US Patent Application, 2024
Patent Details
This method classifies products into categories using textual descriptions and a combination of classifiers, including index-based, encyclopedia-based, Bayes' rule-based, and embeddings classifiers.