Hi, I'm
Vaishak Girish Kumar
MS in AI at SUNY Buffalo. Building hallucination-resistant VLMs for medical imaging and observability tools for LLM pipelines.
01 / About
About Me
I'm an AI/ML researcher focused on building systems that are both powerful and trustworthy. My current work centers on hallucination-resistant vision-language models for medical imaging and developer tools for understanding RAG pipeline behavior.
I believe the next frontier in AI isn't just better models — it's models we can actually trust and understand. That's why I focus on grounding, observability, and explainability in everything I build.
Previously contributed to open-source NLP infrastructure at Scitonic and published two peer-reviewed papers while completing my B.Tech at Presidency University.
M.S. Engineering Science (AI)
SUNY Buffalo · Expected May 2027
B.Tech Computer Science
Presidency University · 2024
Buffalo, NY
Available for remote collaboration
2
Publications
3+
Research Projects
17
OSS Contributions
30%
Perf Improvements
02 / Research
Research & Publications
Focused on making AI systems more reliable and trustworthy, particularly in medical imaging where precision matters most.
ReXGroundingCT
In ProgressTargeting MICCAI 2025
Reference-augmented grounding framework for vision-language models in CT imaging. Uses foveated attention to reduce hallucinations in anatomical predictions by cross-referencing with retrieved similar cases.
- Foveated attention mechanism for focused anatomical analysis
- Reference-augmented retrieval from CT case database
- Targeting 15% reduction in hallucination rate
HippoFormer
In ProgressInternal Research
Transformer-based architecture optimized for hippocampus segmentation from MRI scans. Combines local attention patterns with global context for precise boundary delineation.
- Custom attention patterns for elongated structures
- Multi-scale feature fusion for boundary precision
- State-of-the-art Dice scores on benchmark datasets
Peer-Reviewed Publications
AI-DxMH: Artificial Intelligence Diagnosis for Modern Health
First AuthorV. G. Kumar, M. F. Pasha, A. Prusty, D. Rajeev, G. Ganesan
International Journal of Creative Research Thoughts (IJCRT) · Vol. 12, Issue 1, January 2024
A comprehensive framework for AI-assisted medical diagnosis in resource-constrained environments, achieving 92% accuracy across multiple conditions.
- Developed multi-modal diagnostic pipeline combining patient history, symptoms, and lab results
- Achieved 92% diagnostic accuracy across 15+ common conditions in clinical validation
- Optimized for deployment in resource-constrained healthcare settings with 30% model compression via LoRA
- Implemented explainable AI features for physician trust and regulatory compliance
On-the-fly Prompt Optimization in Multi-Agent Systems: A Comparative Study
Second AuthorM. F. Pasha, V. G. Kumar, A. Prusty, S. Taj
International Journal of Creative Research Thoughts (IJCRT) · Vol. 12, Issue 5, May 2024
Evaluating dynamic prompt optimization strategies in multi-agent LLM architectures for improved task performance.
- Comparative analysis of 5 prompt optimization strategies across multi-agent workflows
- Demonstrated 23% improvement in task completion rates with dynamic prompt refinement
- Introduced feedback-loop mechanism for real-time prompt adaptation between agents
- Benchmarked on complex reasoning tasks requiring multi-step agent coordination
03 / Projects
Featured Projects
A selection of research projects and tools focused on making AI systems more reliable, observable, and trustworthy.
ReXGroundingCT
Reference-augmented grounding for vision language models in medical imaging. Reduces hallucinations in anatomical predictions using foveated attention mechanisms.
Other Projects
Agentic RAG Pipeline
Multi-agent retrieval system with self-correction, query decomposition, and iterative refinement for complex document Q&A.
AI-DxMH
AI-driven diagnostic framework for healthcare. Fine-tuned LLMs achieving 92% accuracy with 30% model compression via LoRA.
LLM Eval Suite
Comprehensive evaluation framework for testing LLM reliability, hallucination rates, and factual accuracy across domains.
Medical VLM Benchmark
Standardized benchmark suite for evaluating vision-language models on medical imaging tasks with clinical ground truth.
04 / Experience
Experience & Skills
Open-Source Developer
Scitonic via Tonic.AI · Remote
Core contributor to LLM pipeline infrastructure through Tonic.AI's open-source program, focusing on NLP tooling and data processing optimization.
Technical Skills
Languages
ML / Deep Learning
LLM / NLP
Infrastructure
05 / Contact
Get in Touch
Interested in collaboration, research opportunities, or discussing AI? I'm always open to connecting with fellow researchers and engineers.
Location
Buffalo, NY
Eastern Time Zone