Leibniz Supercomputing Centre

AI & ML interests

AI Service Infrastructures, LLM pretraining & fine-tuning on HPC systems, multilingual and low-resource language models (German, Bavarian), LLM evaluation & benchmarking (cultural grounding, dialect competence), quantisation & compact models, AI accelerator evaluation (Cerebras CS-2), energy-efficient AI, hate speech detection, RAG applications, EU AI Factories / HammerHAI (AI for startups, SMEs & industry)

Recent Activity

michaelhoff2024  authored a paper 5 days ago

Mapping Toxic Comments Across Demographics: A Dataset from German Public Broadcasting

michaelhoff2024  authored a paper 5 days ago

Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

michaelhoff2024  authored a paper 5 days ago

BavGround: A Benchmark for Regional Cultural Grounding and Dialect Competence in Bavarian

View all activity

Team members 3