45 citations
- Local Initiatives Support CorporationUS6 papers
- Laboratoire Interdisciplinaire des Sciences du NumériqueFR5 papers
- AIT Austrian Institute of Technology GmbHAT3 papers
- Fraunhofer Institute for Experimental Software EngineeringDE3 papers
- Université Paris-SaclayFR3 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- Graz University of TechnologyAT2 papers
- Laboratoire d'Intégration des Systèmes et des TechnologiesFR2 papers
- Siemens (Germany)DE2 papers
- Subsea Technologies (United Kingdom)GB2 papers
- University of HullGB2 papers
- Virtual Vehicle Research GmbH (Austria)AT2 papers
25 papers
Sparse Coverage: Semantic Center Representations for Patent Prior-Art Retrieval
You Zuo, Kim Gerdes, Éric de la Clergerie +1
Patent prior-art retrieval is a recall-oriented search task over long and highly structured technical documents. Dense retrieval improves semantic matching, but single-vector repre…
The Grammar Does the Work: Functional vs. Lexical Dependency Length Minimization Across Universal Dependencies
Kim Gerdes
Dependency length minimization (DLM) is a well-documented processing universal, but previous studies report a single mean dependency distance (MDD) per language, obscuring variatio…
Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench
Younes Djemmal, You Zuo, Kim Gerdes +1
Patent retrieval underpins critical decisions in innovation, examination, and IP strategy, yet progress has been hampered by the absence of benchmarks that reflect the diversity of…
Digital twin-based hybrid framework for steam generator clogging prognostics
Edgar Jaber, Emmanuel Remy, Vincent Chabridon +5
We present a hybrid framework to support prognostics of the clogging degradation phenomenon in tube support plates for digital twins of steam generators in pressurized water reacto…
The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound
Clément Morand, Anne-Laure Ligozat, Aurélie Névéol
Recent Machine Learning (ML) approaches have shown increased performance on benchmarks at the cost of escalating compute demands. Hardware, algorithmic and carbon optimizations hav…
Augmentation-based Domain Generalization and Joint Training from Multiple Source Domains for Whole Heart Segmentation
Franz Thaler, Darko Stern, Gernot Plank +1
As the leading cause of death worldwide, cardiovascular diseases motivate the development of more sophisticated methods to analyze the heart and its substructures from medical imag…