Publications associées à SKILL: Structured Knowledge Infusion for Large Language Models

Publications associées (42)

Collaborative AI Agents in the Era of Large Language Models

Developing agents that can reliably act on our behalf is central to artificial intelligence (AI). These agents must seamlessly interact with tools, like search engines and databases, and collaborate. In this thesis, we study the abstractions, methods, and ...

EPFL2025

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Juan Pablo Zuluaga Gomez

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition (ASR) on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are train ...

Institute of Electrical and Electronics Engineers2025

On the conversational persuasiveness of GPT-4

Francesco Salvi, Robert West

Early work has found that large language models (LLMs) can generate persuasive content. However, evidence on whether they can also personalize arguments to individual attributes remains limited, despite being crucial for assessing misuse. This preregistere ...

Springer Science and Business Media LLC2025

Adapting Fine-Grained Cross-View Localization to Areas Without Fine Ground Truth

Zimin Xia

Given a ground-level query image and a geo-referenced aerial image that covers the query’s local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works have focused on dev ...

Springer Science and Business Media Deutschland GmbH2025

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

Karl El Hajal

Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcrib ...

Institute of Electrical and Electronics Engineers Inc.2025

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

Pascal Fua

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

Springer Science and Business Media Deutschland GmbH2025

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Mattia Atzeni

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

EPFL2024

Ontology-based Knowledge Representation for Traditional Martial Arts

Sarah Irene Brutton Kenderdine, Yumeng Hou

Traditional martial arts are treasures of humanity's knowledge and critical carriers of sociocultural memories throughout history. However, such treasured practices have encountered various challenges in knowledge transmission and now feature many entries ...

2024

Augmenting large language models with chemistry tools

Andres Camilo Marulanda Bran, Carlo Baldassari, Philippe Schwaller, Oliver Tobias Schilter

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ...

Nature Portfolio2024

Social-Transmotion: Promptable Human Trajectory Prediction

Alexandre Massoud Alahi, Saeed Saadatnejad, Yang Gao, Kaouther Messaoud Ben Amor

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

2024

Quasi-operando Transmission Electron Microscopy Diagnostics for Electrocatalytic Processes in Liquids

Vasiliki Tileli

It is of great interest to the energy community to understand how the mechano-physico-chemical phenomena that eventually lead to device degradation are related to the startup, operation, and shutdown phases. For electrocatalytic systems operating in liquid ...

Swiss Chemical Soc2024

Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling

Robert West, Maxime Jean Julien Peyrard, Marija Sakota

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has consistently be ...

Assoc Computing Machinery2024

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

Pierre Vandergheynst, Milos Vasic, Renata Khasanova, Francesco Craighero

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, Renata Khasanova, Francesco Craighero

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

Driving and suppressing the human language network using large language models

Martin Schrimpf

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Nature Portfolio2024

Knowledge Distillation for Face Recognition Using Synthetic Data With Dynamic Latent Sampling

Hatef Otroshi Shahreza

State-of-the-art face recognition models are computationally expensive for mobile applications. Training lightweight face recognition models also requires large identity-labeled datasets, raising privacy and ethical concerns. Generating synthetic datasets ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2024

Echoing Swiss Coloniality. Land, Archive and Visuality between Brazil and Switzerland

Denise Bertschi

Informed by longstanding artistic practice, this doctoral thesis approaches entanglements of Swiss coloniality in Brazil and Switzerland under the lens of land, archive, and visuality. The enduring legacies of imperial capitalism in the former Colonia Leop ...

EPFL2024

Involvement of prelimbic cortex neurons and related circuits in the acquisition of a cooperative learning by pairs of rats

Maria del Carmen Sandi Perez, Elias Georges Gebara

Social behaviors such as cooperation are crucial for mammals. A deeper knowledge of the neuronal mechanisms underlying cooperation can be beneficial for people suffering from pathologies with impaired social behavior. Our aim was to study the brain activit ...

Springer2024

Bioengineering functional organoid models across scales

Tania Hübscher

The last two decades have seen the development of organoid models for many different tissues and organs. Organoids are three-dimensional organ-mimetics derived from stem or progenitor cells comprising various specialized cell types, resembling the architec ...

EPFL2024

Text-to-Microstructure Generation Using Generative Deep Learning

Jamie Paik, Xiaoyang Zheng

Designing novel materials is greatly dependent on understanding the design principles, physical mechanisms, and modeling methods of material microstructures, requiring experienced designers with expertise and several rounds of trial and error. Although rec ...

Wiley-V C H Verlag Gmbh2024