Aditya Adiga

MOSSAIC explores how AI risks and failure modes change across computational substrates, architectures, and deployment contexts. The work focuses on why safety interventions that succeed in one setting often fail when we try to transfer it directly to another. We are working towards building frameworks that capitalise on AI capabilities to generate substrate-sensitive mitigation strategies, proposing a family of safety interventions rather than a uniform solution. This work contributes conceptual and theoretical grounding for substrate flexibility as a core problem in AI safety research.

This project investigates interfaces for AI systems can support collective sensemaking to facilitate genuine human interaction and discernment. I designed an epistemic interface that backgrounds AI while preserving context, structure, and interpretive agency. Conversations are represented as directed acyclic graphs to maintain thematic relationships and enable non-disruptive navigation. The system supports bookmarking and marking potential insights, which can later be used to generate AI-assisted formalisms tailored to specific research interests. Alongside the technical work, I also made philosophical contributions to ideas around AI interfaces that enable meaningful human participation in increasingly AI-integrated environments, with relevance to AI safety and collaborative research.

This project explores MRI-based classification of Major Depressive Disorder using three-dimensional convolutional neural networks. I designed and iteratively refined model architectures and built training and inference pipelines to support systematic experimentation. I applied Grad-CAM–based visualisation techniques to analyse model activations and identify salient brain regions. The work emphasises understanding model behaviour alongside predictive performance.

Designed an OCR-based pipeline for extracting structured information from scanned invoices, using image registration, template matching, and preprocessing to support robust performance across real-world document formats.

I worked on semantic segmentation of complex tumour microenvironments in whole-slide histopathology images. Using a UNET++-based architecture, I developed models to identify tumours, stroma, and surrounding tissue under conditions of high biological variability. Collaborated closely with a pathologist to annotate underrepresented regions and iteratively refine model performance. The resulting system achieved approximately 80% intersection-over-union while remaining robust to heterogeneous tissue structure.

Building on earlier segmentation work, this project focuses on identifying tumour-infiltrating lymphocytes within inflamed stroma regions. I fine-tuned Detectron2-based instance segmentation models and integrated them with upstream tumour microenvironment predictions. Model outputs were validated with domain experts to ensure relevance for downstream immunotherapy analysis.

This project investigates regression-based biomarker scoring using multiple instance learning. I built feature extraction pipelines based on histopathology foundation models and experimented with several MIL strategies. Model outputs were evaluated not only for predictive accuracy but also for biological plausibility and clinical applicability.

I developed a parallelised pipeline for large-scale whole-slide image processing using VIPS. The system stitches approximately eight million image tiles into pyramidal TIFF images and overlays heatmaps to support interpretation of model outputs. End-to-end processing time was reduced from several hours to under ten minutes, significantly improving scalability.

This project focused on integrating AI inference pipelines with an in-house pathology image viewer. I designed workflows informed by user interviews to align model outputs with clinical interpretability requirements. API-level integration linked image storage, predictions, and visualisation layers, improving usability and enabling smoother diagnostic and research workflows.