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

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In this article, we propose a novel approach for the localization of electromagnetic interference (EMI) sources based on the concept of compressive sensing and metalenses. We show that using the spatial and frequency dispersion offered by the metalens, we ...

This article unites different disciplinary debates on ‘southern innovation’, ‘theory from the South’, and ‘decolonisation of knowledge’ in order to discuss existing understandings around the role of Africa in the production of health-related knowledge, pub ...

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better internalize knowledge from a structured data, such as a knowledge graph, or from ...

The perception, physiology, behavior, and performance of building occupants are influenced by multi-domain exposures: the simultaneous presence of multiple environmental stimuli, i.e., visual, thermal, acoustic, and air quality. Despite being extensive, th ...

Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g. reviews and doc ...

Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsup ...

Zero knowledge plays a central role in cryptography and complexity. The seminal work of Ben-Or et al. (STOC 1988) shows that zero knowledge can be achieved unconditionally for any language in NEXP, as long as one is willing to make a suitable physical assu ...

As distribution shifts are inescapable in realistic clinical scenarios due to inconsistencies in imaging protocols, scanner vendors, and across different centers, well-trained deep models incur a domain generalization problem in unseen environments. Despit ...

A Concideration of Typologies for Housing the Sick as a Spatial Manifestation of knowledge. ...

Transformer-based language models trained on large text corpora have enjoyed immense popularity in the natural language processing community and are commonly used as a starting point for downstream tasks. While these models are undeniably useful, it is a c ...

Adaptability and ease of programming are key features necessary for a wider spread of robotics in factories and everyday assistance. Learning from demonstration (LfD) is an approach to address this problem. It aims to develop algorithms and interfaces such ...

With the application requirements of wireless technology in implantable bioelectronics, knowledge of the fundamental limits for implanted antennas becomes critical. In this work, we investigated the variation of maximum power density within simplified body ...

Test-time domain adaptation aims to adapt a source pretrained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems are running in n ...

Action-oriented, transformative, and transdisciplinary approaches are increasingly heralded as promising tools that enable researchers not only to produce new knowledge about a situation, but also to actively engage in tackling it; however, such approaches ...

Efficient sampling of complex high-dimensional probability distributions is a central task in computational science. Machine learning methods like autoregressive neural networks, used with Markov chain Monte Carlo sampling, provide good approximations to s ...

In this thesis, we present a theory of value for the design and analysis of service ecosystems. The theory is based on general systems thinking. The concept of a system is used for relating knowledge from different disciplines (such as software engineering ...

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

Chat with Graph Search

A Compressive Sensing Framework for EMI Source Localization Using a Metalens Structure: Localization Beyond the Diffraction Limit

Examining African contributions to global health: Reflections on knowledge circulation and innovation

SKILL: Structured Knowledge Infusion for Large Language Models

Quality criteria for multi-domain studies in the indoor environment: Critical review towards research guidelines and recommendations

End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

Mechanical intelligence for learning embodied sensor-object relationships

Spatial Isolation Implies Zero Knowledge Even in a Quantum World

OptTTA: Learnable Test-Time Augmentation for Source-Free Medical Image Segmentation Under Domain Shift

Horizontal Healing

Interpreting Language Models Through Knowledge Graph Extraction

Product of experts for robot learning from demonstration

On the Maximum Power Density of Implanted Antennas within Simplified Body Phantoms

Continual Test-Time Domain Adaptation

Explore, engage, empower: methodological insights into a transformative mixed methods study tackling the COVID-19 lockdown

Unbiased Monte Carlo cluster updates with autoregressive neural networks

A Theory of Value for Service Ecosystems