6 papers
The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models
Christoph Walser, Mauricio Fadel Argerich, Jonathan Fürst
Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spectrum. We study this trade-o…
WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs
Mauricio Fadel Argerich, Jonathan Fürst, Marta Patiño-Martínez
Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to…
Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts
Farhad Nooralahzadeh, Omid Rohanian, Yi Zhang +2
When a Vision-Language Model (VLM) sees a blue banana and answers "yellow", is the problem of perception or arbitration? We explore the question in ten VLMs with various sizes and…
Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
Mauricio Fadel Argerich, Jonathan Fürst, Marta Patiño-Martínez
While the large energy consumption of Large Language Models (LLMs) is recognized by the community, system operators lack guidance for energy-efficient LLM inference deployments tha…
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…
AgenticIE: An Adaptive Agent for Information Extraction from Complex Regulatory Documents
Gaye Colakoglu, Gürkan Solmaz, Jonathan Fürst
Declaration of Performance (DoP) documents, mandated by EU regulation, specify characteristics of construction products, such as fire resistance and insulation. While this informat…