↓Skip to main content

🏢 Sorbonne Université

Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
·2753 words·13 mins· loading · loading
AI Generated Machine Learning Optimization 🏢 Sorbonne Université
This paper rigorously analyzes biased adaptive stochastic gradient descent (SGD), proving convergence to critical points for non-convex functions even with biased gradient estimations. The analysis c…
Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
·3736 words·18 mins· loading · loading
AI Generated Machine Learning Meta Learning 🏢 Sorbonne Université
GEPS enhances parametric PDE solver generalization by using adaptive conditioning, achieving superior performance with limited data.
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
·3676 words·18 mins· loading · loading
Machine Learning Deep Learning 🏢 Sorbonne Université
AROMA: Attentive Reduced Order Model with Attention enhances PDE modeling with local neural fields, offering efficient processing of diverse geometries and superior performance in simulating 1D and 2D…
A Concept-Based Explainability Framework for Large Multimodal Models
·7122 words·34 mins· loading · loading
AI Generated Multimodal Learning Vision-Language Models 🏢 Sorbonne Université
CoX-LMM unveils a novel concept-based explainability framework for large multimodal models, extracting semantically grounded multimodal concepts to enhance interpretability.