Giorgio Giannone
YOU?
Author Swipe
View article: Feedback-Driven Vision-Language Alignment with Minimal Human Supervision
Feedback-Driven Vision-Language Alignment with Minimal Human Supervision Open
Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for extensive, high-quality image-text training data. Curation of…
View article: Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling Open
Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must be able to learn long-range dependencies without overfitti…
View article: NITO: Neural Implicit Fields for Resolution-free Topology Optimization
NITO: Neural Implicit Fields for Resolution-free Topology Optimization Open
Topology optimization is a critical task in engineering design, where the goal is to optimally distribute material in a given space for maximum performance. We introduce Neural Implicit Topology Optimization (NITO), a novel approach to acc…
View article: From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design
From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design Open
Engineering design is undergoing a transformative shift with the advent of AI, marking a new era in how we approach product, system, and service planning. Large language models have demonstrated impressive capabilities in enabling this shi…
View article: Constraining Generative Models for Engineering Design with Negative Data
Constraining Generative Models for Engineering Design with Negative Data Open
Generative models have recently achieved remarkable success and widespread adoption in society, yet they often struggle to generate realistic and accurate outputs. This challenge extends beyond language and vision into fields like engineer…
View article: Accelerating material design with the generative toolkit for scientific discovery
Accelerating material design with the generative toolkit for scientific discovery Open
With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful representations learned from datasets to speed up the formulation …
View article: Diffusing the Optimal Topology: A Generative Optimization Approach
Diffusing the Optimal Topology: A Generative Optimization Approach Open
Topology Optimization seeks to find the best design that satisfies a set of constraints while maximizing system performance. Traditional iterative optimization methods like SIMP can be computationally expensive and get stuck in local minim…
View article: Unifying Molecular and Textual Representations via Multi-task Language Modelling
Unifying Molecular and Textual Representations via Multi-task Language Modelling Open
The recent advances in neural language models have also been successfully applied to the field of chemistry, offering generative solutions for classical problems in molecular design and synthesis planning. These new methods have the potent…
View article: Just Mix Once: Worst-group Generalization by Group Interpolation
Just Mix Once: Worst-group Generalization by Group Interpolation Open
Advances in deep learning theory have revealed how average generalization relies on superficial patterns in data. The consequences are brittle models with poor performance with shift in group distribution at test time. When group annotatio…
View article: Accelerating Material Design with the Generative Toolkit for Scientific Discovery
Accelerating Material Design with the Generative Toolkit for Scientific Discovery Open
With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful representations learned from datasets to speed up the formulation …
View article: Clear Cell Carcinoma Arising in an Abdominal Wall Cesarean Section Scar: A Case Report With Description of Pathological and Molecular Features
Clear Cell Carcinoma Arising in an Abdominal Wall Cesarean Section Scar: A Case Report With Description of Pathological and Molecular Features Open
Clear cell carcinoma is a clinically and biologically distinct type of carcinoma predominantly encountered in the ovary and endometrium. In the ovary, it is frequently associated with endometriosis, which is a well-known risk factor. Endom…
View article: Uniportal thoracoscopy combined with laparoscopy as minimally invasive treatment of esophageal cancer
Uniportal thoracoscopy combined with laparoscopy as minimally invasive treatment of esophageal cancer Open
A 67-year-old man was referred to our attention for management of esophageal adenocarcinoma, localized at the level of the esophagogastric junction and obstructed the 1/3 of the esophageal lumen. Due to the extension of the disease (T3N1M0…