Publications

Published research on deep learning, image captioning, and AI systems.

Moral Preferences of LLMs Under Directed Contextual Influence

P. Blandfort, T. Karayil, U. Pawar, R. Graham, A. McKenzie, D. Krasheninnikov

arXiv preprint · Feb 2026

Moral benchmarks for LLMs typically use context-free prompts, implicitly assuming stable preferences. We study how directed contextual influences reshape decisions in trolley-problem-style moral triage settings and find that contextual influences often significantly shift decisions, baseline preferences are a poor predictor of directional steerability, influences can backfire, and reasoning reduces average sensitivity but amplifies the effect of biased few-shot examples.

LLMsAI SafetyEthicsMoral Reasoning

Rethinking Software Design with Large Language Models Intelligent Interfaces

C. N. Coelho, H. Xiong, T. Karayil, S. Koratala, R. Shang, J. Bollinger, M. Shabar, S. Nair

International Conference on Multimodal Interaction (ICMI) · Apr 2025

The advancement of Large Language Models (LLMs) has led to a rapid expansion of their applications, including in software design. We propose a new approach to refine system specifications using natural language-based interfaces, enabling software engineers and architects to iteratively improve software development documentation, ensuring a clearer definition of system behavior, required resources, and dependencies.

LLMsSoftware EngineeringAI Agents

Effort and Size Estimation in Software Projects with Large Language Model-based Intelligent Interfaces

C. N. Coelho, H. Xiong, T. Karayil, S. Koratala, R. Shang, J. Bollinger, M. Shabar, S. Nair

arXiv preprint · Feb 2024

The advancement of Large Language Models (LLM) has also resulted in an equivalent proliferation in its applications. Through the example of UI-based user stories, we provide a comparison against traditional methods and propose a new way to enhance specifications of natural language-based questions that allows for the estimation of development effort by taking into account data sources, interfaces and algorithms.

LLMsSoftware EstimationAI

AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style

S. Frolov, A. Sharma, J. Hees, T. Karayil, F. Raue, A. Dengel

German Conference on Pattern Recognition (GCPR) · Mar 2021

We propose a method for attribute controlled image synthesis from layout which allows to specify the appearance of individual objects without affecting the rest of the image. We extend a state-of-the-art approach for layout-to-image generation to additionally condition individual objects on attributes.

GANsImage SynthesisComputer Vision

The Focus-Aspect-Value Model for Explainable Prediction of Subjective Visual Interpretation

T. Karayil, P. Blandfort, J. Hees, A. Dengel

International Conference on Multimedia Retrieval (ICMR) · Jun 2019

We propose the Focus-Aspect-Value (FAV) model to structure the process of capturing subjectivity in image processing, and introduce a novel dataset following this way of modeling. We find that incorporating context information based on tensor multiplication outperforms the default way of information fusion (concatenation).

ExplainabilityVisual AttributesDeep Learning

Fusion Strategies for Learning User Embeddings with Neural Networks

P. Blandfort, T. Karayil, F. Raue, J. Hees, A. Dengel

IEEE International Joint Conference on Neural Networks (IJCNN) · Jan 2019

We analyze the effect on embedding quality caused by several fusion strategies in neural networks for learning user embeddings from rating data. We propose Pair-Distance Correlation, a novel measure for evaluating embedding quality, and find that prediction performance not necessarily reflects embedding quality.

User EmbeddingsNeural NetworksFusion Strategies