Nous publions ce que nous apprenons.
Essais, sorties open-source et notes de terrain depuis la production. Décryptages de modèles fondationaux, jeux de données, et ce qui change quand le modèle rencontre le terrain.
Demystifying Robotic Foundational Models: GROOT N1
Alright, let's talk about NVIDIA's GR00T N1. In our series on Demystifying robotic Foundation Models, it introduces unique approaches to data augmentation, synthetic trajectories, and leveraging action-less videos.
Demystifying Robotic Foundational Models: Pi0
Demystifying robotic foundational models: from Pi0 to Gemini-Robotics & Groot N1. Deep dive into Vision-Language-Action models, flow matching, and the training recipe for generalist robots.
AI System for Cattle Weight Estimation Using Smartphones
Building an AI system for cattle weight estimation using smartphones. Our research enables farmers and ranchers to accurately estimate the weight of cattle by taking a photo, eliminating physical weighing scales.
DementiaNet — Early Dementia Detection Through Speech Analysis
How we built the largest publicly available longitudinal dataset for dementia prediction, using spontaneous speech analysis to detect cognitive impairment 10-15 years before symptoms appear.
What We Learned Building Our First LLM-Based App: AVVA
Lessons from building AVVA, an AI veterinary platform powered by multiple LLMs. Exploring fine-tuning, memory management, model selection, and the challenges of providing helpful medical advice.
Dernière mise à jour: 2026-05-08