Karishma Thakrar

Chloe Pomeroy, Aleksandar Pramov, Karishma Thakrar et al.

This paper explores the applications of quantum annealing (QA) and classical simulated annealing (SA) to a suite of combinatorial optimization problems in machine learning, namely feature selection, instance selection, and clustering. We formulate each task as a Quadratic Unconstrained Binary Optimization (QUBO) problem and implement both quantum and classical solvers to compare their effectiveness. For feature selection, we propose several QUBO configurations that balance feature importance and redundancy, showing that quantum annealing (QA) produces solutions that are computationally more efficient. In instance selection, we propose a few novel heuristics for instance-level importance measures that extend existing methods. For clustering, we embed a classical-to-quantum pipeline, using classical clustering followed by QUBO-based medoid refinement, and demonstrate consistent improvements in cluster compactness and retrieval metrics. Our results suggest that QA can be a competitive and efficient tool for discrete machine learning optimization, even within the constraints of current quantum hardware.

Karishma Thakrar, Shreyas Basavatia, Akshay Daftardar

Dermatological care via telemedicine often lacks the rich context of in-person visits. Clinicians must make diagnoses based on a handful of images and brief descriptions, without the benefit of physical exams, second opinions, or reference materials. While many medical AI systems attempt to bridge these gaps with domain-specific fine-tuning, this work hypothesized that mimicking clinical reasoning processes could offer a more effective path forward. This study tested seven vision-language models on medical visual question answering across six configurations: baseline models, fine-tuned variants, and both augmented with either reasoning layers that combine multiple model perspectives, analogous to peer consultation, or retrieval-augmented generation that incorporates medical literature at inference time, serving a role similar to reference-checking. While fine-tuning degraded performance in four of seven models with an average 30% decrease, baseline models collapsed on test data. Clinical-inspired architectures, meanwhile, achieved up to 70% accuracy, maintaining performance on unseen data while generating explainable, literature-grounded outputs critical for clinical adoption. These findings demonstrate that medical AI succeeds by reconstructing the collaborative and evidence-based practices fundamental to clinical diagnosis.

Karishma Thakrar, Nick Young

This paper explores the application of large language models (LLMs) to extract nuanced and complex job features from unstructured job postings. Using a dataset of 1.2 million job postings provided by AdeptID, we developed a robust pipeline to identify and classify variables such as remote work availability, remuneration structures, educational requirements, and work experience preferences. Our methodology combines semantic chunking, retrieval-augmented generation (RAG), and fine-tuning DistilBERT models to overcome the limitations of traditional parsing tools. By leveraging these techniques, we achieved significant improvements in identifying variables often mislabeled or overlooked, such as non-salary-based compensation and inferred remote work categories. We present a comprehensive evaluation of our fine-tuned models and analyze their strengths, limitations, and potential for scaling. This work highlights the promise of LLMs in labor market analytics, providing a foundation for more accurate and actionable insights into job data.

Karishma Thakrar, Jiangqin Ma, Max Diamond et al.

Predicting the impact of single-point amino acid mutations on protein stability is essential for understanding disease mechanisms and advancing drug development. Protein stability, quantified by changes in Gibbs free energy ($ΔΔG$), is influenced by these mutations. However, the scarcity of data and the complexity of model interpretation pose challenges in accurately predicting stability changes. This study proposes the application of deep neural networks, leveraging transfer learning and fusing complementary information from different models, to create a feature-rich representation of the protein stability landscape. We developed four models, with our third model, ThermoMPNN+, demonstrating the best performance in predicting $ΔΔG$ values. This approach, which integrates diverse feature sets and embeddings through latent transfusion techniques, aims to refine $ΔΔG$ predictions and contribute to a deeper understanding of protein dynamics, potentially leading to advancements in disease research and drug discovery.

Karishma Thakrar, Katrina Lawrence, Kyle Howard

Stylistic text generation plays a vital role in enhancing communication by reflecting the nuances of individual expression. This paper presents a novel approach for generating text in a specific speaker's style across different languages. We show that by leveraging only 100 lines of text, an individuals unique style can be captured as a high-dimensional embedding, which can be used for both text generation and stylistic translation. This methodology breaks down the language barrier by transferring the style of a speaker between languages. The paper is structured into three main phases: augmenting the speaker's data with stylistically consistent external sources, separating style from content using machine learning and deep learning techniques, and generating an abstract style profile by mean pooling the learned embeddings. The proposed approach is shown to be topic-agnostic, with test accuracy and F1 scores of 74.9% and 0.75, respectively. The results demonstrate the potential of the style profile for multilingual communication, paving the way for further applications in personalized content generation and cross-linguistic stylistic transfer.

Karishma Thakrar

Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information present in textual and structured data remains a challenge. To address this, a novel GRAG framework, Dynamic Graph Retrieval-Agumented Generation (DynaGRAG), is proposed to focus on enhancing subgraph representation and diversity within the knowledge graph. By improving graph density, capturing entity and relation information more effectively, and dynamically prioritizing relevant and diverse subgraphs and information within them, the proposed approach enables a more comprehensive understanding of the underlying semantic structure. This is achieved through a combination of de-duplication processes, two-step mean pooling of embeddings, query-aware retrieval considering unique nodes, and a Dynamic Similarity-Aware BFS (DSA-BFS) traversal algorithm. Integrating Graph Convolutional Networks (GCNs) and Large Language Models (LLMs) through hard prompting further enhances the learning of rich node and edge representations while preserving the hierarchical subgraph structure. Experimental results demonstrate the effectiveness of DynaGRAG, showcasing the significance of enhanced subgraph representation and diversity for improved language understanding and generation.