Machine Learning and COgnitive SoftwaRE (CORE)

Our research group explores the intersection of artificial intelligence, cognitive computing, and software engineering. Our work focuses on developing machine learning models that enhance cognitive software systems, enabling adaptive, efficient, and interpretable AI solutions. We investigate topics such as neural network architectures, reasoning in language models, and AI-driven decision-making. By bridging theoretical insights with practical applications, our research aims to advance the capabilities of intelligent software systems in diverse domains, from natural language processing to complex decision support systems.

Partner Institutions:

Members

Support Staff

Mareike Kroeller

Administrative Assistant

Steffen Ottow

IT Specialist

DCBM: Data-Efficient Visual Concept Bottleneck Models

ICML 2025

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages

NAACL 2025

Shedding Light on Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model

ICLR 2025 (DL4C Workshop)

Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models

ICLR 2025 (FM-Wild Workshop)

Which LIME should I trust? Concepts, Challenges, and Solutions

XAI 2025

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

ICLR 2025

Disentangling Exploration of Large Language Models by Optimal Exploitation

arXiv

DRAMA at the PettingZoo: Dynamically Restricted Action Spaces for Multi-Agent Reinforcement Learning Frameworks

HICSS 2024

RAISE the Bar: Restriction of Action Spaces for Improved Social Welfare and Equity in Traffic Management

AAMAS 2024