3 papers
cs.CL2026
Bench360: Benchmarking Local LLM Inference from 360 Degrees
Linus Stuhlmann, Mauricio Fadel Argerich, Jonathan Fürst
Running LLMs locally has become increasingly common, but users face a complex design space across models, quantization levels, inference engines, and serving scenarios. Existing in…
cs.IR2026
Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation
Linus Stuhlmann, Michael Alexander Saxer, Jonathan Fürst
Biomedical question-answering (QA) systems require effective retrieval and generation components to ensure accuracy, efficiency, and scalability. This study systematically examines…
cs.SD2025
Evaluating the Effectiveness of Transformer Layers in Wav2Vec 2.0, XLS-R, and Whisper for Speaker Identification Tasks
Linus Stuhlmann, Michael Alexander Saxer
This study evaluates the performance of three advanced speech encoder models, Wav2Vec 2.0, XLS-R, and Whisper, in speaker identification tasks. By fine-tuning these models and anal…