↓Skip to main content

🏢 Sorbonne University

Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms
·1976 words·10 mins· loading · loading
AI Theory Optimization 🏢 Sorbonne University
This research introduces a novel framework that overcomes the brittleness of Pareto-optimal learning-augmented algorithms by enforcing smoothness in performance using user-specified profiles and devel…
Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
·6925 words·33 mins· loading · loading
AI Generated Multimodal Learning Vision-Language Models 🏢 Sorbonne University
Frozen LLMs surprisingly excel at multimodal tasks; this paper reveals that their success stems from an implicit multimodal alignment effect, paving the way for efficient LMMs.