Modèles d'IA

Les modèles d'IA prédisent des résultats à partir de leurs données d'entraînement. Ils peuvent fonctionner dans tous les domaines, tels que les nombres, le texte ou le multimédia.

Explorer : catégorie

LLM

Benchmark des modèles tabulaires : Performance sur 19 jeux de données

Modèles d'IAMai 22

We benchmarked 7 widely used tabular learning models across 19 real-world datasets, covering ~260,000 samples and over 250 total features, with dataset sizes ranging from 435 to nearly 49,000 rows. Our goal was to understand top-performing model families for datasets of different sizes and structure (e.g. numeric vs.

Modèles d'IAMai 15

Modèles Fondamentaux du Monde : 10 Cas d'Usage

Training robots and autonomous vehicles (AVs) in the physical world can be costly, time-consuming and risky. World Foundation Models offer a scalable alternative by enabling realistic simulations of real-world environments. These models accelerate development and deployment in robotics, AVs, and other domains by reducing reliance on physical testing.

Modèles d'IAMai 7

Comparer les grands modèles de vision : GPT-4o vs YOLOv8n

Large vision models (LVMs) can automate and improve visual tasks such as defect detection, medical diagnosis, and environmental monitoring. We benchmarked three object detection models: YOLOv8n, DETR, and GPT-4o Vision, across 1,000 images each, measuring metrics such as mAP@0.5, inference speed, FLOPs, and parameter count.

Modèles d'IAAvr 24

Modèles de langage visuel comparés à la reconnaissance d'images

Can advanced Vision Language Models (VLMs) replace traditional image recognition models? To find out, we benchmarked 16 leading models across three paradigms: traditional CNNs (ResNet, EfficientNet), VLMs ( such as GPT-4.1, Gemini 2.5), and Cloud APIs (AWS, Google, Azure).

Modèles d'IAAvr 15

Comparer les modèles relationnels fondamentaux

We benchmarked SAP-RPT-1-OSS against gradient boosting (LightGBM, CatBoost) on 17 tabular datasets spanning the semantic-numeral spectrum, small/high-semantic tables, mixed business datasets, and large low-semantic numerical datasets. Our goal is to measure where a relational LLM’s pretrained semantic priors may provide advantages over traditional tree models and where they face challenges under scale or low-semantic structure.

Modèles d'IAFév 10

Modèles de base pour les séries temporelles : cas d'utilisation et avantages

Time series foundation models (TSFMs) build on advances in foundation models from natural language processing and vision. Using transformer-based architectures and large-scale training data, they achieve zero-shot performance and adapt across sectors such as finance, retail, energy, and healthcare.