Giorgio Giannone

I am an Applied Scientist at Amazon, working on generative models.

I completed my PhD at the Technical University of Denmark (DTU), supervised by Ole Winther and Søren Hauberg. During my PhD, I was a visiting researcher at MIT and UCL, collaborated with the MIT-IBM AI Lab, and interned at Microsoft Research, IBM Research, and Amazon Science.


blind-date blind-date blind-date blind-date blind-date blind-date blind-date blind-date blind-date

CV  /  GitHub  /  LinkedIn  /  Scholar

I am an engineer and researcher broadly interested in Probabilistic Machine Learning, Perception and Geometry,
with a focus on Conditional Diffusion Models, Language Models Adaptation, Few-Shot Generation,
and Hierarchical Variational Inference.


I am interested in the generalization and adaptation capabilities of hierarchical generative models.
Large generative models trained on billions of data points demonstrate remarkable few-shot adaptation, enabling them to tackle novel tasks with just a few examples. However, these properties tend to manifest only at scale and are not present in smaller models, which are commonly used in engineering and scientific discovery where data is costly to gather and computational resources are limited.
My research aims to bridge the gap in adaptation capabilities between large and small generative models, leveraging the tools of hierarchical inference and using the training dataset to encourage adaptation at inference time.


NITO: Neural Implicit Fields for Resolution-free Topology Optimization
Amin Heyrani Nobari, Giorgio Giannone, Lyle Regenwetter, Faez Ahmed
Preprint, arXiv, 2024

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 accelerate topology optimization problems using deep learning. NITO stands out as one of the first frameworks to offer a resolution-free and domain-agnostic solution in deep learning-based topology optimization. NITO synthesizes structures with up to seven times better structural efficiency compared to SOTA diffusion models and does so in a tenth of the time. In the NITO framework, we introduce a novel method, the Boundary Point Order-Invariant MLP (BPOM), to represent boundary conditions in a sparse and domain-agnostic manner, moving away from expensive simulation-based approaches.


Constraining Generative Models for Engineering Design with Negative Data
Lyle Regenwetter*, Giorgio Giannone*, Akash Srivastava, Dan Gutfreund, Faez Ahmed
Preprint, arXiv, 2024

Generative models have recently achieved remarkable success and widespread adoption in society, yet they still often struggle to generate realistic and accurate outputs. This challenge extends beyond language and vision into fields like engineering design, where safety-critical engineering standards and non-negotiable physical laws tightly constrain what outputs are considered acceptable. In this work, we introduce two approaches to guide models toward constraint-satisfying outputs using negative data -- examples of what to avoid.


From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design
Cyril Picard*, Kristen M. Edwards*, Anna C. Doris, Brandon Man, Giorgio Giannone, Md Ferdous Alam, Faez Ahmed
Under Review, 2024

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 shift. Yet, with text as their only input modality, they cannot leverage the large body of visual artifacts that engineers have used for centuries and are accustomed to. This gap is addressed with the release of multimodal vision language models, such as GPT-4V, enabling AI to impact many more types of tasks. In light of these advancements, this paper presents a comprehensive evaluation of GPT-4V, a vision language model, across a wide spectrum of engineering design tasks, categorized into four main areas: Conceptual Design, System-Level and Detailed Design, Manufacturing and Inspection, and Engineering Education Tasks.


Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
Giorgio Giannone, Akash Srivastava, Ole Winther, Faez Ahmed
Neural Information Processing Systems, NeurIPS, 2023

Generative models have had a profound impact on vision and language, paving the way for a new era of multimodal generative applications. While these successes have inspired researchers to explore using generative models in science and engineering to accelerate the design process and reduce the reliance on iterative optimization, challenges remain. Specifically, engineering optimization methods based on physics still outperform generative models when dealing with constrained environments where data is scarce and precision is paramount. To address these challenges, we introduce Diffusion Optimization Models (DOM) and Trajectory Alignment (TA), a learning framework that demonstrates the efficacy of aligning the sampling trajectory of diffusion models with the optimization trajectory derived from traditional physics-based methods.


Improving Precision in Language Models Learning from Invalid Samples
Niels Jakob Larsen*, Giorgio Giannone*, Ole Winther, Kai Blin
Generative AI and Biology Workshop, NeurIPS, 2023

Language Models are powerful generative tools capable of learning intricate patterns from vast amounts of unstructured data. Nevertheless, in domains that demand precision, such as science and engineering, the primary objective is to obtain an exact and accurate answer. Precision takes precedence in these contexts. In specialized tasks like chemical compound generation, the emphasis is on output accuracy rather than response diversity. Traditional self-refinement methods are ineffective for such domain-specific input/output pairs, unlike general language tasks. In this study, we introduce invalid2valid, a powerful and general post-processing mechanism that can significantly enhance precision in language models for input/output tasks spanning different domains and specialized applications.


Enhancing Language Models for Technical Domains with Dynamic Token Injection
Giorgio Giannone, Neil Tenenholtz, James Hall, Nicolo Fusi, David Alvarez-Melis
Generative AI and Biology Workshop, NeurIPS, 2023

Large language models (LLMs) are rapidly advancing the frontier of natural language understanding and generation. Their generalist nature, while adept at handling a wide range of tasks, often lacks the depth and precision required by highly specialized and rapidly evolving technical domains, such as genomics and engineering design. Fine-tuning these models for specific domains can be effective but requires large amounts of data and compromises their general reasoning capabilities. In this work, we introduce a scalable method to infuse specialized knowledge into generalist language models by dynamically extending their vocabulary with specialist tokens. By using a lightweight functional mapping on an extended vocabulary and adjusting the logit distribution, we enable the model to grasp domain-specific nuances.


Learning from Invalid Data: On Constraint Satisfaction in Generative Models
Giorgio Giannone*, Lyle Regenwetter*, Akash Srivastava*, Dan Gutfreund, Faez Ahmed
Diffusion Models Workshop, NeurIPS, 2023

Generative models have demonstrated impressive results in vision, language, and speech. However, even with massive datasets, they struggle with precision, generating physically invalid or factually incorrect data. This is particularly problematic when the generated data must satisfy constraints, for example, to meet product specifications in engineering design or to adhere to the laws of physics in a natural scene. To improve precision while preserving diversity and fidelity, we propose a novel training mechanism that leverages datasets of constraint-violating data points, which we consider invalid.


Unifying Molecular and Textual Representations via Multi-task Language Modelling
Dimitrios Christofidellis*, Giorgio Giannone*, Jannis Born, Ole Winther, Teodoro Laino, Matteo Manica
International Conference on Machine Learning, ICML, 2023

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 potential to optimize laboratory operations and fuel a new era of data-driven automation in scientific discovery. However, specialized models are still typically required for each task, leading to the need for problem-specific fine-tuning and neglecting task interrelations. Here, we propose a multi-domain, multi-task language model to solve a wide range of tasks in both the chemical and natural language domains. By leveraging multi-task learning, our model can handle chemical and natural language concurrently, without requiring expensive pre-training on single domains or task-specific models.


Diffusing the Optimal Topology: A Generative Optimization Approach
Giorgio Giannone, Faez Ahmed
International Design Engineering Technical Conferences, IDETC, 2023

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 minima, limiting their applicability to complex or large-scale problems. Recently, deep generative models, such as Generative Adversarial Networks and Diffusion Models, conditioned on constraints and physics fields have shown promise, but they require extensive pre-processing and surrogate models for improving performance. 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.


Accelerating material design with the generative toolkit for scientific discovery
Manica & the GT4SD Team (Core Contributor)
Nature npj Computational Materials, 2023

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 of novel hypotheses with the potential to impact material discovery broadly. We present the Generative Toolkit for Scientific Discovery (GT4SD). This extensible open-source library enables scientists, developers, and researchers to train and use state-of-the-art generative models to accelerate scientific discovery focused on organic material design.


Few-Shot Diffusion Models
Giorgio Giannone, Didrik Nielsen, Ole Winther
Score-Based Methods Workshop, NeurIPS, 2022

Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties can be attributed to parameter sharing in the generative hierarchy, as well as a parameter-free diffusion-based inference procedure. In this paper, we present Few-Shot Diffusion Models (FSDM), a framework for few-shot generation leveraging conditional DDPMs. FSDMs are trained to adapt the generative process conditioned on a small set of images from a given class by aggregating image patch information using a set-based Vision Transformer (ViT). At test time, the model is able to generate samples from previously unseen classes conditioned on as few as 5 samples from that class. We empirically show that FSDM can perform few-shot generation and transfer to new datasets taking full advantage of the conditional DDPM.


SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
Giorgio Giannone, Ole Winther
International Conference on Machine Learning, ICML, 2022

A few-shot generative model should be able to generate data from a novel distribution by only observing a limited set of examples. 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. We extend current latent variable models for sets to a fully hierarchical approach with an attention-based point to set-level aggregation and call our method SCHA-VAE for Set-Context-Hierarchical-Aggregation Variational Autoencoder. We explore likelihood-based model comparison, iterative data sampling, and adaptation-free out-of-distribution generalization.


Just Mix Once: Worst-group Generalization by Group Interpolation
Giorgio Giannone, Serhii Havrylov, Jordan Massiah, Emine Yilmaz, Yunlong Jiao
Distribution Shifts Workshop, NeurIPS, 2021

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 annotation is available, we can use robust optimization tools to tackle the problem. However, identification and annotation are time-consuming, especially on large datasets. A recent line of work leverages self-supervision and oversampling to improve generalization on minority groups without group annotation. We propose to unify and generalize these approaches using a class-conditional variant of mixup tailored for worst-group generalization. Our approach, Just Mix Once (JM1), interpolates samples during learning, augmenting the training distribution with a continuous mixture of groups.


Hierarchical Few-Shot Generative Models
Giorgio Giannone, Ole Winther
Meta-Learning Workshop, NeurIPS, 2021

A few-shot generative model should be able to generate data from a distribution by only observing a limited set of examples. In few-shot learning the model is trained on data from many sets from different distributions sharing some underlying properties such as sets of characters from different alphabets or sets of images of different type objects. We study a latent variables approach that extends the Neural Statistician to a fully hierarchical approach with an attention-based point to set-level aggregation. We extend the previous work to iterative data sampling, likelihood-based model comparison, and adaptation-free out of distribution generalization.


Transformation-aware Variational Autoencoder
Giorgio Giannone, Saeed Saremi, Jonathan Masci, Christian Osendorfer
Technical Report, 2020

We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. This is achieved in the form of a generative model structured such that the group of transformations that act in the input space is instead represented by latent variables which are linear operators that only act in the latent space. In the family of hierarchical graphical models that emerges, the latent space is populated by higher order objects which are inferred jointly with the latent representations they act on.


Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
Giorgio Giannone, Asha Anoosheh, Alessio Quaglino, Pierluca D'Oro, Marco Gallieri, Jonathan Masci
Interpretable Inductive Biases and Physically Structured Learning Workshop, NeurIPS, 2020

Event-based cameras are novel, efficient sensors inspired by the human vision system, generating an asynchronous, pixel-wise stream of data. Learning from such data is generally performed through heavy preprocessing and event integration into images. This requires buffering of possibly long sequences and can limit the response time of the inference system. In this work, we instead propose to directly use events from a DVS camera, a stream of intensity changes and their spatial coordinates. This sequence is used as the input for a novel asynchronous RNN-like architecture, the Input-filtering Neural ODEs.


No Representation without Transformation
Giorgio Giannone, Jonathan Masci, Christian Osendorfer
Bayesian Deep Learning and Perception as Generative Reasoning Workshops, NeurIPS , 2019

We propose to extend Latent Variable Models with a simple idea: learn to encode not only samples but also transformations of such samples. This means that the latent space is not only populated by embeddings but also by higher order objects that map between these embeddings. We show how a hierarchical graphical model can be utilized to enforce desirable algebraic properties of such latent mappings.


Learning Common Representation from RGB and Depth Images
Giorgio Giannone, Boris Chidlovskii
Multimodal Learning and Applications Workshop, CVPR, 2019

We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images. We revise the state of art based on the RGB and depth feature fusion, where both modalities are assumed to be available at train and test time. We propose a new architecture where the feature fusion is replaced with a common deep representation. Combined with an encoder-decoder type of the network, the architecture can jointly learn models for semantic segmentation and depth estimation based on their common representation.


GT4SD: Generative Toolkit for Scientific Discovery
GT4SD Team, 2022

The GT4SD (Generative Toolkit for Scientific Discovery) is an open-source platform to accelerate hypothesis generation in the scientific discovery process. It provides a library for making state-of-the-art generative AI models easier to use.


2d Topology Optimization

We built a dataset of optimized topologies and intermediate optimization steps at low-resolution (64x64) and high-resolution (256x256) with constraints.

  • 50K low-resolution optimized topologies.
  • 60K high-resolution optimizer topologies.
  • 250K low-resolution intermediate steps.
  • 300K high-resolution intermediate steps.


3d Topology Optimization

We built a multifidelity dataset of 300K optimized topologies with constraints.

  • 150K beams.
  • 100K plates.
  • 50K l-shapes.


Course 02456 Deep learning (Fall 2020)

Course 02477 Bayesian Machine Learning (Spring 2021)

Course 02460 Advanced Machine Learning (Spring 2022)

Course 02456 Deep learning (Fall 2022)


Method and Apparatus to Learn Generative Optimization Models
Giorgio Giannone, Akash Srivastava, Faez Ahmed
filing, 2023


Method and apparatus for semantic segmentation and depth completion using a convolutional neural network
Boris Chidlovskii, Giorgio Giannone
US Patent US11263756B2, 2022


Few-Shot Generative Models: Learning Generative Models from Limited Data
Giorgio Giannone
PhD's Thesis, Machine Learning, Technical University of Denmark, 2023


Learning Common Representation for Scene Understanding
Giorgio Giannone
Master's Thesis, Data Science, Sapienza University of Rome, 2018


Bubble Dynamics in Turbulent Shear Flows
Giorgio Giannone
Master's Thesis, Mechanical Engineering, Sapienza University of Rome, 2016

the original