1 citations · 1 across the 8 of their papers we have counts for
8 papers
Holonic Active Distillation for Scalable Multi-Agent Learning in Multi-Sensor Systems
Dani Manjah, Tim Bary, Benoît Macq +1
The rapid expansion of sensor-based networks introduces major challenges in scalability, adaptability, and knowledge transfer, especially in open environments where new subsystems…
Localized Conformal Prediction for Image Classification with Vision-Language Models
Clément Fuchs, Tim Bary, Benoît Macq
Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage guarantees. Full conditional…
CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification
Mikael Turkoglu, Tim Bary, Vincent Thielens +2
While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-siz…
Optimizing Resources for On-the-Fly Label Estimation with Multiple Unknown Medical Experts
Tim Bary, Tiffanie Godelaine, Axel Abels +1
Accurate ground truth estimation in medical screening programs often relies on coalitions of experts and peer second opinions. Algorithms that efficiently aggregate noisy annotatio…
Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment
Dani Manjah, Tim Bary, Benoît Gérin +2
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central…
No Need for Learning to Defer? A Training Free Deferral Framework to Multiple Experts through Conformal Prediction
Tim Bary, Benoît Macq, Louis Petit
AI systems often struggle to provide reliable predictions across all inputs, motivating hybrid human-AI decision-making. Existing Learning to Defer (L2D) approaches address this by…
Conformal Predictions for Human Action Recognition with Vision-Language Models
Bary Tim, Fuchs Clément, Macq Benoît
Human-in-the-Loop (HITL) systems are essential in high-stakes, real-world applications where AI must collaborate with human decision-makers. This work investigates how Conformal Pr…
Designing Pre-training Datasets from Unlabeled Data for EEG Classification with Transformers
Tim Bary, Benoit Macq
Transformer neural networks require a large amount of labeled data to train effectively. Such data is often scarce in electroencephalography, as annotations made by medical experts…