8 papers
Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery
Hendrik Droste, Christian Medeiros Adriano, Kathrin Korte +1
Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities. Understanding the internal…
Interference-Aware Cross-Application Placement: A Multi-Objective Optimization Approach for Microservice Clusters
Iqra Zafar, Christian Medeiros Adriano, Holger Giese
In modern cloud architectures, multiple applications often run within the same clustered environment, sharing underlying resources. This resource sharing can cause interference amo…
From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models
Leonard Engmann, Christian Medeiros Adriano, Holger Giese
Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific c…
CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation
Jan-Niklas Klein, Sona Ghahremani, Christian Medeiros Adriano +1
Rovers rely on perception to maintain spatial maps that encode both objects and sensor quality (e.g., range reliability, lighting artifacts, data density), guiding data fusion, emb…
From Program Slices to Causal Clarity: Evaluating Faithful, Actionable LLM-Generated Failure Explanations via Context Partitioning and LLM-as-a-Judge
Julius Porbeck, Christian Medeiros Adriano, Holger Giese
Large language model (LLM)-based debugging systems can generate failure explanations, but these explanations may be incomplete or incorrect. Misleading explanations are harmful for…
Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles
Zainab Rehan, Christian Medeiros Adriano, Sona Ghahremani +1
Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacki…
Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments
Kathrin Korte, Christian Medeiros Adriano, Sona Ghahremani +1
[Context] Multi-agent reinforcement learning (MARL) has achieved notable success in environments where agents must learn coordinated behaviors. However, transferring knowledge acro…
Mind the Gap Between Synthetic and Real: Utilizing Transfer Learning to Probe the Boundaries of Stable Diffusion Generated Data
Leonhard Hennicke, Christian Medeiros Adriano, Holger Giese +2
Generative foundation models like Stable Diffusion comprise a diverse spectrum of knowledge in computer vision with the potential for transfer learning, e.g., via generating data t…