Publications related to Foundation models

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

Social-Transmotion: Promptable Human Trajectory Prediction

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

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

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

Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes

Antoine Bosselut, Jibril Albachir Frej, Paola Mejia Domenzain, Luca Mouchel, Tatjana Nazaretsky, Seyed Parsa Neshaei, Thiemo Wambsganss

Writing high-quality procedural texts is a challenging task for many learners. While example-based learning has shown promise as a feedback approach, a limitation arises when all learners receive the same content without considering their individual input ...

2024

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

David Atienza Alonso, Marina Zapater Sancho, Luis Maria Costero Valero, Darong Huang, Ali Pahlevan

Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limi ...

2024

How to Support Students to Cultivate Psychological Safety in their Teams

Francesco Mondada, Yousef Jalali

The importance of psychological safety in teams has been demonstrated in different settings. Team performance improves when team climate allows team members to be their authentic selves, to ask questions and raise concerns comfortably. However, it is less ...

EPFL2024

Efficient local linearity regularization to overcome catastrophic overfitting

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

2024

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Yi Wu

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

2024

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.

Foundation models

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

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

Social-Transmotion: Promptable Human Trajectory Prediction

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

Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

How to Support Students to Cultivate Psychological Safety in their Teams

Efficient local linearity regularization to overcome catastrophic overfitting

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Graph Chatbot

Chat with Graph Search

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

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

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

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

Social-Transmotion: Promptable Human Trajectory Prediction

Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study on Cooking Recipes

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

How to Support Students to Cultivate Psychological Safety in their Teams

Efficient local linearity regularization to overcome catastrophic overfitting

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange