Medical Imaging AI · Computer Vision · Multimodal Learning

Hello, I'm

Lakshmikar ReddyPolamreddy.

PhD in Computer Science and Mathematics

AI Research Scientist

Computer Vision · Medical Imaging · Multimodal AI

Developing intelligent systems that see, reason, and generate. My research spans computer vision, multimodal AI, medical imaging, and generative models—connecting foundational research with real-world applications.

Explore My Research ↗Connect With Me Download CV ↓

AI Researcher

About Me

Advancing Medical AIThrough Vision & Reasoning.

Developing intelligent medical imaging systems through computer vision, multimodal reasoning, and generative AI.

Academic Background

AI Researcher

PhD in Computer Science and Mathematics

Yeshiva University

I am a PhD researcher in Computer Science and Mathematics at Yeshiva University, specializing in computer vision, multimodal learning, and medical artificial intelligence.

My research investigates how visual understanding, language-guided reasoning, and geometric learning can be integrated to develop more capable and reliable AI systems. My work spans medical image segmentation, generative modeling, diffusion models, and three-dimensional vision.

I am passionate about translating fundamental research into practical AI applications and contributing to research scientist, applied scientist, and computer vision engineering teams.

Research Specializations

Computer VisionMedical ImagingMultimodal AIMedical Image SegmentationGenerative AIDiffusion ModelsMamba / State-Space ModelsVision-Language ModelsLLMs & RAGGeometric Learning

Career & Academic Journey

Experience that connects research and practice

Industry delivery, academic research, and teaching across AI, medical imaging, data analytics, and engineering.

Industry Experience

Jun–Aug 2025 · Jun–Aug 2026

Data Scientist

Quantegy Analytics Inc.

New York, NY

Built a correctional healthcare analytics product with 60+ interactive reports covering patient census, medications, laboratory services, chronic care, PPD screening, and staff productivity.
Developed SIOP analytics for a global endurance sports organization, combining athlete-registration data and predictive forecasts for sales, event capacity, and inventory planning.
Engineered data pipelines and interactive applications using Python, Pandas, SQL, Snowflake, and Streamlit.

Sep–Dec 2023

AI Intern

Modali Consulting

New York, NY

Developed an LLM-powered plugin for dynamic form generation, integrating APIs and prompting with a Streamlit conversational interface.

Feb 2014 – Jun 2022

Technical Leader

Cyient Ltd.

Hyderabad, India

Built Tableau dashboards for operational KPIs, including first-time-right, on-time delivery, and utilization; used Python for data preparation, exploratory analysis, and visualization.

2011–2013

Senior Design Engineer

Tech Mahindra

India

Contributed to engineering design and technical delivery in cross-functional project environments.

Jun 2007 – Aug 2010

Senior Design Engineer

Infotech Enterprises IT Services Pvt Ltd

Hyderabad, India

Worked on engineering design and technical project delivery.

Research & Teaching Experience

Jan 2024 – Present

Research Assistant

Yeshiva University

New York, NY

Developed multimodal architectures for reasoning-guided 2D and 3D medical image segmentation, combining vision-language models, encoder–decoder networks, and geometric representations.
Researched medical image synthesis using diffusion models, Transformers, and Mamba architectures; investigated information-theoretic limits of diffusion models and developed the MedNet dataset and a medical image generation framework.
Introduced a positional reasoning score for evaluating spatial reasoning and visual–text consistency.

May–Jul 2025 · Jul–Aug 2026

Graduate Adjunct Instructor

Yeshiva University

New York, NY

Delivered introductory statistics instruction covering probability, statistical inference, and hypothesis testing.
Guided students through applied statistical analysis using R, RStudio, and Excel.

Sep–Dec 2025 · Jan–May 2026

Graduate Teaching Assistant

Yeshiva University

New York, NY

Supported graduate-level Deep Learning and Neural Networks coursework and technical problem-solving.
Assisted with experimental workflows, neural network evaluation, and interpretation of model results.

May–Aug 2024

Adjunct Faculty

Yeshiva University

New York, NY

Mentored MS Artificial Intelligence students on VetMed GPT, generative image models, and retrieval-augmented generation (RAG) chatbots.
Provided guidance on model benchmarking, experimental evaluation, and technical research writing.

Education

PhD in Mathematics and Computer Science

Yeshiva University

Jan 2024 – Present · Expected Dec 2026

MS in Artificial Intelligence

Yeshiva University

Dec 2023

BTech in Mechanical Engineering

Sri Venkateswara University

May 2007

Certifications & Recognition

AWS Certified Cloud Practitioner

Advanced Certificate Programme in Data Science — IIIT Bangalore

Academic Service

Peer reviewer for NeurIPS, ICLR, BMVC, IEEE Healthcom, ICASSP, and Knowledge-Based Systems.

Technical Foundation

Areas of Expertise

Research expertise and engineering capabilities across modern computer vision and artificial intelligence.

01 / Expertise

Computer Vision & Medical AI

Medical ImagingImage Segmentation3D Computer VisionCNNsGeometric Learning

02 / Expertise

Generative & Multimodal AI

Diffusion ModelsGANsMamba / State-Space ModelsVision-Language ModelsLLMs, LoRA & RAG

03 / Expertise

Deep Learning & Frameworks

PyTorchTransformersNumPy & PandasMatplotlib & SeabornModel Evaluation

04 / Expertise

Programming, Data & Platforms

Python & SQLRSnowflakeStreamlitTableauETL PipelinesStatistical AnalysisData Visualization

Research Contributions

Research & Publications

Research in computer vision, multimodal learning, generative AI, and medical image analysis.

Published Papers

5 papers

CVPR 2026Published

CG-Reasoner: Centroid-Guided Positional Reasoning Segmentation for Medical Imaging with a Robust Visual-Text Consistency Metric

Computer Vision

View Paper ↗

Information Fusion 2025Published

The Deficit of New Information in Diffusion Models: A Focus on Diverse Samples

Generative AI

View Paper ↗

WACV 2025 WorkshopPublished

Confident Pseudo-Labeled Diffusion Augmentation for Canine Cardiomegaly Detection

Medical AI

View Paper ↗

ACM/IEEE CHASE 2025Published

Leapfrog Latent Consistency Model (LLCM) for Medical Images Generation

Generative AI

View Paper ↗

Future Technologies Conference 2023Published

LaksNet: An End-to-End Deep Learning Model for Self-Driving Cars in Udacity Simulator

Computer Vision

View Paper ↗

Accepted Papers

2 papers

IEEE Healthcom 2026Accepted

MedNet and U²-ViT: A Nested Vision Transformer Diffusion Framework for Diverse Medical Images Generation

Diffusion Models

ICONIP 2026Accepted

WD-Mamba: A W-Mamba Diffusion Model for Enhancing Image Synthesis

Generative AI

Research Impact & Recognition

Featured in University News

Research stories published by Yeshiva University, highlighting contributions to medical AI, generative models, and autonomous driving.

June 8, 2026Yeshiva University

Medical AI · CVPR 2026

Like a Doctor, AI System Identifies and Describes Tumors in Medical Scans

Yeshiva University features Lakshmikar's lead-author research on CG-Reasoner, connecting medical image segmentation with spatial language reasoning.

Read University Article ↗

November 2, 2025Yeshiva University

Generative AI · Information Fusion

Study Reveals AI Diffusion Models Mostly Rearrange, Not Reinvent, What They Learn

University coverage of Lakshmikar's co-authored research on information novelty and diverse samples in diffusion models.

Read University Article ↗

December 15, 2023Yeshiva University

Autonomous Driving · Research Award

Researchers Using AI to Reduce Accidents in Self-Driving Cars Receive Award

Yeshiva University highlights the Emerging Research Award received by Lakshmikar Polamreddy and Youshan Zhang for LaksNet.

Read University Article ↗

Official Research Award · 2023

Emerging Research Award

Presented to Youshan Zhang and Lakshmikar Reddy Polamreddy at the Future Technologies Conference 2023 for “LaksNet: An End-to-End Deep Learning Model for Self-Driving Cars in Udacity Simulator.”

November 2–3, 2023 · San Francisco, USA

View Official Certificate ↗

Let's Connect

Let's build the future ofintelligent systems.

Open to research collaborations and opportunities in AI research, applied science, and computer vision.

Get in Touch ↗Download CV ↓

GitHub ↗LinkedIn ↗Google Scholar ↗

lakshmikarpolamreddy@gmail.com