HalluShift: Measuring Distribution Shifts towards Hallucination Detection in Large Language Models
Benchmarks internal distribution shifts to flag hallucination-prone generations.
Research Publications
All
LLM/MLLM
Medical
Vision
Core ML
Heritage
Hallushift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs Accepted
Medical Report Generation with Fine‑Tuned Large Language Models Workshop
Explores instruction‑tuning strategies for reliable radiology‑style generation.
From Complexity to Clarity: Transforming Chest X‑ray Reports with Chained Prompting
A chained prompting recipe (CPIR‑MR) to translate radiology reports into layperson‑friendly prose.
Concurrent Density Estimation with Wasserstein Autoencoders: Some Statistical Insights
Characterizes information preservation and generation consistency under the Wasserstein metric.
Near‑Perfect Image Super‑Resolution: Exploring Multiple Divergence Measures in Fully Convolutional GAN Under review
On Robust Cross Domain Alignment Under review
Improved Alzheimer’s Disease Detection with Dynamic Attention Guided Multi‑modal Fusion
Digital Restoration of Cultural Heritage With Data‑Driven Computing: A Survey
Do Pre‑processing and Class Imbalance Matter to the Deep Image Classifiers for COVID‑19 Detection? An Explainable Analysis
On Regenerative and Discriminative Learning from Digital Heritages: A Fractal Dimension based Approach
Face Mask Recognition using Advanced Face Cut Algorithm for COVID‑19 Safety Measures
Medium Writings | @arkaprabha17
Pinned
Demystifying Diffusion Models: An In‑Depth Evolution — with a Companion Podcast
Diffusion models have taken over generative modeling — simpler training, strong sample quality…
Step‑by‑Step: Enable the Medium Partner Program (with screenshots)
A short walkthrough to activate monetization on Medium…
How will your model react? RTX 3070 vs. M1 vs. Colab GPU
A quick primer on DL hardware differences and when they matter…