Publications associées (690)

Docta Manus Drawing Structures 2023

Patricia Guaita, Raffael Baur, Enrique Corres Sojo, David Carlos Fernandez-Ordoñez Hernandez

Drawing constitutes a very powerful and critical tool of conceptual design. Drawing constructs thought, it acts as a communication interface between the work and the mind and between different disciplines; it is the most powerful language of communication ...
2024

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Pierre Vandergheynst, Milos Vasic, Francesco Craighero, Renata Khasanova

Under resource constraints, LLMs are usually fine- tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new ...
2024

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Pierre Vandergheynst, Milos Vasic, Francesco Craighero, Renata Khasanova

Under resource constraints, LLMs are usually fine-tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new t ...
2024

Notes on Drawing: interior material lines

Patricia Guaita, Raffael Baur

The essential aspects of drawing cannot be taught theoretically. They can only be learned through practice by creating a certain intimacy with the work. The action of hand drawing initiates a transformative bodily experience generating intensities, frictio ...
Park Books2023

Building a Knowledge Graph of Chinese Kung Fu Masters From Heterogeneous Bilingual Data

Yumeng Hou, Lin Yuan

Various endeavours into semantic web technologies and ontology engineering have been made within the organisation of cultural data, facilitating public access to digital assets. Although models for conceptualising objects have reached a certain level of ma ...
2023

Unlocking a multimodal archive of Southern Chinese martial arts through embodied cues

Sarah Irene Brutton Kenderdine, Yumeng Hou, Fadel Mamar Seydou

Purpose: Despite being an authentic carrier of various cultural practices, the human body is often underutilised to access the knowledge of human body. Digital inventions today have created new avenues to open up cultural data resources, yet mainly as appa ...
2023

Sustaining Knowledge and Governing its Infrastructure in the Digital Age: An Integrated View

Simon François Dumas Primbault, Pierre Henri Marcel Mounier

Preprint of a programmatic article on the governance and ecology of digital knowledge infrastructures stemming from a year of seminars and workshops led between September 2021 and June 2022 at the Laboratory for the history of science and technology (LHST) ...
2023

Improving Generalization of Pretrained Language Models

Rabeeh Karimi Mahabadi

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...
EPFL2023

Atomic scale volume and grain boundary diffusion elucidated by in situ STEM

Johann Michler, Xavier Maeder, Laszlo Pethö, Amit Sharma

Diffusion is one of the most important phenomena studied in science ranging from physics to biology and, in abstract form, even in social sciences. In the field of materials science, diffusion in crystalline solids is of particular interest as it plays a p ...
Berlin2023

Appropriations and Uses of Travel Time

Ludy Juliana González Villamizar

Time has always been a central factor in understanding the challenges of daily mobility. For a long time, and still today, methods of economic evaluation of transport projects have monetized time savings so that they can be included in the cost–benefit ana ...
ISTE Wiley2023

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.