Dario García-Gasulla

Revisiting TuRTLe: A Comprehensive Evaluation of LLMs for RTL Generation

Miquel Albertí, Cristian Gutierrez-Gomez, Dario García-Gasulla, Emanuele Parisi et autres

Rapid advancements in LLMs have driven the adoption of generative AI in domains like Electronic Design Automation (EDA). Within the field of software development, EDA presents unique challenges derived from specific requirements of generated RTL code; RTL code must not only be …

es (code pays fourni par la source)

HEART Attacks: Healthcare Evaluation of Adversarial RobusTness

Martín Suárez-Fernández, Enrique Lopez-Cuena, Jaume Guasch-Martí, Dario García-Gasulla et autres

Large Vision-Language Models (LVLMs) have shown potential for integrating visual and textual information, yet they continue to exhibit limitations in visual reasoning and robustness, a particular concern in high-stakes domains such as healthcare. Prior robustness evaluations remain limited in breadth, typically focusing …

es (code pays fourni par la source)

Scalable Deep Learning Framework for Global High-Resolution Land Use Reconstruction

Amirpasha Mozaffari, Marina Castaño, Stefano Materia, Étienne Tourigny et autres

Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly driven by the uncertainties affecting the land surface representation and variability in Earth system models. To address this limitation, we present a data-driven framework AI4Land, for generating high-resolution …

Scalable Deep Learning Framework for Global High-Resolution Land Use Reconstruction

Amirpasha Mozaffari, Marina Castaño, Stefano Materia, Étienne Tourigny et autres

Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly driven by the uncertainties affecting the land surface representation and variability in Earth system models. To address this limitation, we present a data-driven framework AI4Land, for generating high-resolution …

es (code pays fourni par la source)

The Aloe Family recipe for open and specialized healthcare LLMs

Dario García-Gasulla, Jordi Bayarri-Planas, Ashwin Kumar Gururajan, Enrique Lopez-Cuena et autres

The growing interest in the application of Large Language Models (LLMs) for healthcare comes with a demand for better open-source LLMs, and stronger reassurances regarding their performance. To advance in this direction, this work conducts a thorough and transparent study of LLM …

es (code pays fourni par la source)

LLM Translation of Compiler Intermediate Representation

Andrea Valenzuela Ramirez, Cristian Gutierrez-Gomez, Marta Barroso, Dario García-Gasulla et autres

GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create significant barriers for cross-toolchain interaction, limiting the reuse of compiler frontends, …

LLM Translation of Compiler Intermediate Representation

Andrea Valenzuela Ramirez, Cristian Gutierrez-Gomez, Marta Barroso, Dario García-Gasulla et autres

GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create significant barriers for cross-toolchain interaction, limiting the reuse of compiler frontends, …

es (code pays fourni par la source)

RuC: HDL-Agnostic Rule Completion Benchmark Generation

Arnau Ayguadé Domingo, Miquel Albertí-Binimelis, Cristian Gutierrez-Gomez, Emanuele Parisi et autres

Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RTL) development increasingly attractive. Mimicking the behavior of inline code assistants, many benchmarks evaluate LLMs' capabilities in code completion, either assessing the generation …

RuC: HDL-Agnostic Rule Completion Benchmark Generation

Arnau Ayguadé Domingo, Miquel Albertí-Binimelis, Cristian Gutierrez-Gomez, Emanuele Parisi et autres

Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RTL) development increasingly attractive. Mimicking the behavior of inline code assistants, many benchmarks evaluate LLMs' capabilities in code completion, either assessing the generation …

es (code pays fourni par la source)

NotSoTiny: A Large, Living Benchmark for RTL Code Generation

Razine Moundir Ghorab, Emanuele Parisi, Cristian Gutierrez, Miquel Albertí-Binimelis et autres

LLMs have shown early promise in generating RTL code, yet evaluating their capabilities in realistic setups remains a challenge. So far, RTL benchmarks have been limited in scale, skewed toward trivial designs, offering minimal verification rigor, and remaining vulnerable to data contamination. …

NotSoTiny: A Large, Living Benchmark for RTL Code Generation

Razine Moundir Ghorab, Emanuele Parisi, Cristian Gutierrez, Miquel Albertí-Binimelis et autres

LLMs have shown early promise in generating RTL code, yet evaluating their capabilities in realistic setups remains a challenge. So far, RTL benchmarks have been limited in scale, skewed toward trivial designs, offering minimal verification rigor, and remaining vulnerable to data contamination. …

Immunosuppressed patients with COVID-19 pneumonia in ICU: clinical characteristics and factors influencing outcomes

Flavia Galli, Edoardo Forin, Ana Motos, Francisco José Molina Saldarriaga et autres

INTRODUCTION: COVID-19 severely impacted global health, especially older adults and those with comorbidities. Immunosuppressed patients are at high risk for severe outcomes, yet studies yield conflicting mortality rates for this group. This study examines the clinical characteristics and outcomes of immunosuppressed (IS) …

es, it, fr, co, al (code pays fourni par la source)