no code implementations • 8 Jan 2025 • Giorgio Giannone, Ruoteng Li, Qianli Feng, Evgeny Perevodchikov, Rui Chen, Aleix Martinez
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.
no code implementations • CVPR 2025 • Anqi Liang, Ciprian Corneanu, Qianli Feng, Giorgio Giannone, Aleix Martinez
In this work, we define a new standard for assessing object-centric realism that follows a shape-texture breakdown and proposes the first object-centric realism evaluation dataset for synthetic images.
no code implementations • 18 Aug 2024 • Harry Jake Cunningham, Giorgio Giannone, Mingtian Zhang, Marc Peter Deisenroth
Global convolutions have shown increasing promise as powerful general-purpose sequence models.
1 code implementation • 7 Feb 2024 • Amin Heyrani Nobari, Giorgio Giannone, Lyle Regenwetter, Faez Ahmed
We introduce Neural Implicit Topology Optimization (NITO), a novel approach to accelerate topology optimization problems using deep learning.
no code implementations • 21 Nov 2023 • Cyril Picard, Kristen M. Edwards, Anna C. Doris, Brandon Man, Giorgio Giannone, Md Ferdous Alam, Faez Ahmed
Large language models have demonstrated impressive capabilities in enabling this shift.
1 code implementation • 27 Jun 2023 • Lyle Regenwetter, Giorgio Giannone, Akash Srivastava, Dan Gutfreund, Faez Ahmed
Our negative-data generative model (NDGM) formulation easily outperforms classic models, generating 1/6 as many constraint-violating samples using 1/8 as much data in certain problems.
no code implementations • 17 Mar 2023 • Giorgio Giannone, Faez Ahmed
To address these issues, we propose a Generative Optimization method that integrates classic optimization like SIMP as a refining mechanism for the topology generated by a deep generative model.
1 code implementation • 29 Jan 2023 • Dimitrios Christofidellis, Giorgio Giannone, Jannis Born, Ole Winther, Teodoro Laino, Matteo Manica
Here, we propose the first multi-domain, multi-task language model that can solve a wide range of tasks in both the chemical and natural language domains.
Ranked #6 on
Molecule Captioning
on ChEBI-20
no code implementations • 21 Oct 2022 • Giorgio Giannone, Serhii Havrylov, Jordan Massiah, Emine Yilmaz, Yunlong Jiao
Advances in deep learning theory have revealed how average generalization relies on superficial patterns in data.
1 code implementation • 8 Jul 2022 • Matteo Manica, Jannis Born, Joris Cadow, Dimitrios Christofidellis, Ashish Dave, Dean Clarke, Yves Gaetan Nana Teukam, Giorgio Giannone, Samuel C. Hoffman, Matthew Buchan, Vijil Chenthamarakshan, Timothy Donovan, Hsiang Han Hsu, Federico Zipoli, Oliver Schilter, Akihiro Kishimoto, Lisa Hamada, Inkit Padhi, Karl Wehden, Lauren McHugh, Alexy Khrabrov, Payel Das, Seiji Takeda, John R. Smith
With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery.
1 code implementation • 30 May 2022 • Giorgio Giannone, Didrik Nielsen, Ole Winther
At test time, the model is able to generate samples from previously unseen classes conditioned on as few as 5 samples from that class.
1 code implementation • 23 Oct 2021 • Giorgio Giannone, Ole Winther
In few-shot learning the model is trained on data from many sets from distributions sharing some underlying properties such as sets of characters from different alphabets or objects from different categories.
no code implementations • 7 Apr 2020 • Giorgio Giannone, Asha Anoosheh, Alessio Quaglino, Pierluca D'Oro, Marco Gallieri, Jonathan Masci
INODE is trained like a standard RNN, it learns to discriminate short event sequences and to perform event-by-event online inference.
no code implementations • 9 Dec 2019 • Giorgio Giannone, Saeed Saremi, Jonathan Masci, Christian Osendorfer
To explicitly demonstrate the effect of these higher order objects, we show that the inferred latent transformations reflect interpretable properties in the observation space.
no code implementations • 17 Dec 2018 • Giorgio Giannone, Boris Chidlovskii
We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images.