Concept
Transformeur génératif pré-entraîné
Publications associées (136)
The multimodality cell segmentation challenge: toward universal solutions
Sahand Jamal Rahi, Vojislav Gligorovski, Marco Labagnara, Jun Ma, Xin Yang, Maxime Emmanuel Scheder, Yao Zhang, Bo Wang, Yixin Wang, Lin Han
Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...
Nature Portfolio2024MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
Alexandre Massoud Alahi, Mohamed Ossama Ahmed Abdelfattah, Mariam Ahmed Mahmoud Hegazy Hassan
Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...
2024Beyond 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 ...
2024Beyond 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 ...
2024Driving and suppressing the human language network using large language models
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 ...
Berlin2024Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning
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 ...
EPFL2024Social-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 ...
2024GELEX: Generative AI-Hybrid System for Example-Based Learning
Jibril Albachir Frej, Aybars Yazici
Traditional example-based learning methods are often limited by static, expert-created content. Hence, they face challenges in scalability, engagement, and effectiveness, as some learners might struggle to relate to the examples or find them relevant. To a ...
Association for Computing Machinery2024Fly-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 Machinery2024Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models
Auditory research aims in general to lead to understanding of physiological processes. By contrast, the state of the art in automatic speech processing (notably recognition) is dominated by large pre-trained models that are meant to be used as black-boxes. ...
2024