Risultati della ricerca - Furst, Jonathan

ASAG2024: A Combined Benchmark for Short Answer Grading di Meyer, Gérôme, Breuer, Philip, Fürst, Jonathan

Testo

Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs di Colakoglu, Gaye, Solmaz, Gürkan, Fürst, Jonathan

Testo

AgenticIE: An Adaptive Agent for Information Extraction from Complex Regulatory Documents di Colakoglu, Gaye, Solmaz, Gürkan, Fürst, Jonathan

Testo

VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents di Huwiler, Daniel, Stockinger, Kurt, Fürst, Jonathan

Testo

Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation di Stuhlmann, Linus, Saxer, Michael Alexander, Fürst, Jonathan

Testo

Bench360: Benchmarking Local LLM Inference from 360 Degrees di Stuhlmann, Linus, Argerich, Mauricio Fadel, Fürst, Jonathan

Testo

Multi-Modal Data Exploration via Language Agents di Nooralahzadeh, Farhad, Zhang, Yi, Furst, Jonathan, Stockinger, Kurt

Testo

Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures di Argerich, Mauricio Fadel, Fürst, Jonathan, Patiño-Martínez, Marta

Testo

Interactive Ontology Matching with Cost-Efficient Learning di Cheng, Bin, Fürst, Jonathan, Jacobs, Tobias, Garrido-Hidalgo, Celia

Testo

Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries di Fürst, Jonathan, Kosten, Catherine, Nooralahzadeh, Farhad, Zhang, Yi, Stockinger, Kurt

Testo

TextMineX: Data, Evaluation Framework and Ontology-guided LLM Pipeline for Humanitarian Mine Action di Zhou, Chenyue, Solmaz, Gürkan, Cirillo, Flavio, Gashteovski, Kiril, Fürst, Jonathan

Testo

Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts di Nooralahzadeh, Farhad, Rohanian, Omid, Zhang, Yi, Fürst, Jonathan, Stockinger, Kurt

Testo