3D Computer Vision

Anpei Chen (PostDoc)

We plan to design cutting-edge algorithms to enable fast and generalizable 3D reconstruction, novel view synthesis, and 3D-aware image synthesis by combining advances in computer vision and computer graphics. This project includes three main parts: (1) Geometric modeling and reconstruction are fundamental to compute...

3D Perception, Reconstruction, and Understanding of Large-Scale Scenes

Haofei Xu (Ph.D. Student)

This project aims to explore how to enable 3D perception and understanding of large-scale scenes in the following aspects: 1) 3D representation. How to efficiently and effectively represent 3D remains to be an open problem, especially for large-scale scenes. 2) 3D reconstruction and synthesis. Achieving 3D reconstru...

A causal approach to privacy, fairness and distributional robustness in machine learning

Yaxi Hu (Ph.D. Student)

While machine learning becomes an integral component of our daily life, people often overlook the profound consequences these models pose, especially concerning the privacy of the training data and fairness towards its users. Central to solving these problems is the challenge of ensuring generalization under distrib...

A geometric look to understand generalization and robustness of deep learning

Guillermo Ortiz Jiménez (Ph.D. Student)

Years of a fierce competition towards the best results have naturally selected the fittest deep learning algorithms. However, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trust, and fairness of modern AI sys...

Achieving Fair, Accountable and Transparent Machine Learning Models through Graph Theory and Causality

Adrián Arnaiz-Rodríguez (Ph.D. Student)

Machine learning models are becoming the main tools for addressing complex societal problems and are also increasingly deployed to make or support decisions about individuals in many consequential areas of their lives, from justice to healthcare. Therefore, the ethical implications of such decisions, including conce...

Advancing generative models for 3D synthesis

Olga Grebenkova (Ph.D. Student)

The goal of this PhD project is to investigate the potential of generative models in 3D for creating high-quality, realistic objects suitable for various applications. While significant progress has been made in text-to-image synthesis using diffusion models trained on billions of image-text pairs, applying this tec...

AI and Machine learning for Trustworthy Autonomous Intelligent Machines and Systems

Oishi Deb (Ph.D. Student)

This project focuses on theoretical as well as applied research on trustworthy autonomous intelligent machines and systems to ensure better decision-making in safety-critical applications. It will address vulnerabilities and countermeasures of ML and AI algorithms that are being used in Autonomous Systems (AS). Unce...

Analysing the effect of counter-narratives on hateful conversations online

Nicolò Penzo (Ph.D. Student)

While the task of automatically recognising hateful content online has been extensively explored in the last years within the NLP community, what is the best strategy to respond to such messages has only recently entered the research agenda. Specifically, some works in the last few years have tackled the issue of au...

Analyzing Materials through Machine Learning

Vincent Stimper (Ph.D. Student)

Measurement techniques to characterize the properties of materials, such as photoemission spectroscopy, were continuously improved throughout the last decades. This led to a drastic increase of the measured data in terms of size, resolution, and complexity. Analyzing those dataset poses challenges, e.g. processing t...

Application of Neural Networks in Many-Body Physics

Sebastian Sanokowski (Ph.D. Student)

Problems with a large number of interacting particles are ubiquitous in science and key to many future technologies. Recently, the successful application of deep learning methods to such problems led to remarkable progress in statistical mechanics, quantum chemistry and condensed matter physics. We will investigate ...

Asymptotics and Dynamics of Learning, Optimization, and Causality

Yatin Dandi (Ph.D. Student)

Theoretical analysis of the asymptotics of systems involving a large number of interacting entities has enabled massive progress in fields ranging from Statistical Physics, High Dimensional Statistics, Combinatorial Optimization, to the theory of Machine Learning. In this PhD, we aim to build upon the techniques dev...

Automated Painting: Object Modeling, Trajectory Learning and Adaptation

Gabriele Tiboni (Ph.D. Student)

Spray painting is a task commonly performed by robots in industry. Automating this process offers advantages on the consistency of the results and repeatability over even the most skilled human operator, with the further benefit of limiting human exposure to hazardous environments. The goal of this thesis is to redu...

Bayesian deep learning for medical time series

Fedor Sergeev (Ph.D. Student)

Deep learning (DL) has seen tremendous growth in the last 20 years and enabled rapid advances in computer vision, natural language processing, and robotics. However, the direct application of DL methods to healthcare is challenging due to the nature of medical data. Creating specialized data sets for DL in medical a...

Bridging Theory and Algorithms for Lifelong Learning

Marco Ciccone (PostDoc)

One of the most ambitious goals of Artificial Intelligence is to provide an agent with the ability to continually learn in an open-ended scenario. Lifelong Learning, or Continual Learning (CL), explicitly focuses on non-stationary or changing environments, where an agent has to complete a series of partially related...

Causal Inference in Reinforcement Learning

Stephan Bongers (PostDoc)

Recent advances in reinforcement learning have led to automated decision-making systems that perform remarkably well on various tasks. Despite these remarkable achievements, applying reinforcement learning in practice often remains challenging. One major challenge is that one often needs knowledge of the environment...

Causal inference with fewer assumptions

Kirtan Padh (Ph.D. Student)

Causality has recently been seen as a promising path towards designing more reliable machine learning algorithms, in the sense of robustness, domain generalization, fairness, interpretability and more. However, there have also been some criticisms regarding the strong and unrealistic assumptions that causal inferenc...

Causal relationships in nonlinear representation learning

Patrik Reizinger (Ph.D. Student)

The robustness of underlying representations is a key for deploying machine learning systems in real-world applications. This requires both the possibly unique identification of the latent factors themselves and their connections as well. Although the topic is an active research area, there are no satisfactory algor...

Causality in heavy missing data scenarios

Sergio Hernan Garrido Mejia (Ph.D. Student)

Whenever we see the world we rarely observe all the variables of any system of interest at the same time. However, we can create hypotheses of causal relations by combining information of these partially observed scenarios. In this research, we will focus on the question of extracting causal information from scenari...

Cognitive models for Meta-Reinforcement-Learning

Julian Coda-Forno (Ph.D. Student)

The project aims to use cognitive science models and inspiration to develop better Meta-RL agents. Meta-RL is the combination of two disciplines in Machine Learning, Meta-learning and Reinforcement Learning. Meta-learning is the idea inspired by psychology of “learning to learn” in humans, and looks at how an AI can...

Comparison of heterogeneous or uncertain network structures

Diane Duroux (Ph.D. Student)

Seeking reproducibility of findings is an essential part of research. This becomes a tedious and cumbersome task when big data with dependant features or multiple potentially interdependent data sources become available. Earlier work has shown that this is already the case for GWAIS compared to easier GWAS. The main...

Continual Learning

Mohammad Derakhshani (Ph.D. Student)

Despite the promise of artificially intelligent agents, they are known to suffer from catastrophic forgetting when learning over nonstationary data distributions. Continual learning, also known as life-long learning, was introduced to deal with catastrophic forgetting. In this framework, an agent continually learns ...

Continual Multimodal Leaming

Nico Daheim (Ph.D. Student)

Many NLP tasks require incorporating not only textual data but also other modalities, such as images, speech, or software code. In this project, we aim to build systems that can jointly reason over these different modalities with diverse applications, for example in dialog systems. Furthermore, the information that ...

Continual Reinforcement Learning with associative memories

Thomas Schmied (Ph.D. Student)

The current generation of Deep Reinforcement learning systems is primarily designed to solve one particular task in a single stationary environment. However, the real world is non-stationary and dynamic by nature. For Reinforcement learning agents to be useful under these circumstances, they need to have the ability...

Controllable and faithful generation of language in time critical low-resource scenarios

Mayank Jobanputra (Ph.D. Student)

Today's neural generation systems produce fluent text, but are prone to generate factual errors. This is particularly problematic for safety-critical settings such as generation systems that assist human experts in making quick decisions for autonomous systems. The thesis project will focus on generating relevant,...

Cross Modal Neural Architecture Search

Niccolò Cavagnero (Ph.D. Student)

Determining an optimal architecture is key to accurate deep neural networks (DNNs) with good generalisation properties. Neural architecture search (NAS) can potentially reduce the need for application-specific expert designers allowing for a wide-adoption of sophisticated networks in various industries. It has been ...

Cross-domain activity classification from multiple information channels

Chiara Plizzari (Ph.D. Student)

Recognizing human actions from videos is one of the most critical challenges in computer vision since its infancy. An open challenge is that video analysis systems heavily rely on the environment in which the activities are recorded, which inhibits their ability to recognize actions when they are recorded in unfamil...

Curation of Medical Image Data using lnteractive Learning

Stefan Denner (Ph.D. Student)

Artificial intelligence (Al)'s potential applications in medical imaging are vast and significant. One of the chief obstacles to the development and clinical implementation of Al algorithms is the availability of sufficiently large, curated, and representative training data based on expert labeling. Collecting such ...

Dealing with Domain Shift under Resource Constraints

Niclas Popp (Ph.D. Student)

This PhD project aims at addressing two major challenges that deep learning models for perception face when being deployed on edge devices (such as in driver assistance/automated driving, mobile robotics, video surveillance): (i) resources are limited in edge devices and there are hard limits on, e.g., latency and e...

Deep Learning-driven Enhancer Design

Animesh Awasthi (Ph.D. Student)

Understanding the complex regulation of gene expression by non-coding regions of the genome for cell-type-specific transcriptional activity is very challenging. Such regulatory mechanisms are crucial for developing a deeper understanding of human diseases and potential therapeutic strategies. Advancements in high-th...

Discovering causal mechanisms in Single-Cell Omics

Alejandro Tejada (Ph.D. Student)

Single-Cell genomics allow to get a fine resolution of the internal state of a cell. Nevertheless, the dynamics and mechanisms that rule the behaviour of cells are mainly unknown. Due to the enormous number of degrees of freedom, classical scientific approaches may fail at modelling and capturing the complexity of S...

Efficent Medical Segmentation

Jie Liu (Ph.D. Student)

Medical segmentation plays an important role in adaptive radiotherapy. However, current medical segmentation methods require tons of annotated samples to achieve robust result, thus posing great pressure on data annotation. With this project, we focus on developing effecicent medical segmentation alghrithm, thus rec...

Efficient egocentric vision models for the edge

Gabriele Goletto (Ph.D. Student)

With the advent of machines capable, in principle, to cooperate with humans in performing tasks of daily living, it becomes crucial the development of methods to quickly and easily infer human actions from common data. Egocentric vision is rapidly becoming one of the most promising source of information for this pur...

Efficient tuning of quantum devices using machine learning

Lucas Schorling (Ph.D. Student)

The critical challenge in the development of scalable quantum technologies, such as quantum computers, is the increasingly complex and time-consuming task of characterizing and tuning a large number of quantum devices. As the scale of these technologies expands, traditional methods of characterization become intract...

Egocentric Vision for Advanced Human-Robot Cooperation

Simone Peirone (Ph.D. Student)

In recent times, research in robotics devoted a significant effort to the development of compliant manipulators capable of interacting with the surrounding environment safely and effectively. However, while many studies focused on pushing the limits of human-robot interaction with novel control, planning, and task a...

Enhancing Risk-Aware Navigation for Legged Robots in Dynamic Construction Site Environments Using Foundational Language Models and Building Information Maps

Maya Sitaram (Ph.D. Student)

This research aims to advance the autonomous navigation capabilities of legged robots in construction site environments by integrating foundational language models with Building Information Maps (BIM). Robots show immense potential in construction site monitoring, offering the ability to generate detailed 3D maps an...

Explainable AI for Nature Conservation

Diego Marcos (PostDoc)

As Deep Learning gets better at visual tasks, including species identification, the learned reasoning behind its decisions gets increasingly obscure. This is in contrast with the procedures developed by taxonomists, the experts in charge of defining the hierarchy of natural species, for manual species recognition....

Explainable machine learning for causal understanding in neuroscience

Anastasiia Filippova (Ph.D. Student)

Understanding how neural circuits enable behavior is a critical challenge in neuroscience: it has important implications for brain-machine-interfaces (BMIs), robotics, and neuro-rehabilitation. As our ability to record large neural and behavioral data increases, there is growing interest in modeling neural dynamics...

Exploring Inductive Biases in Reinforcement Learning Through Action Spaces

Jan Schneider (Ph.D. Student)

When applying reinforcement learning to robotics, there is a multitude of choices for the action representations. Our experiments demonstrate that this choice generally has a significant impact on learning performance. In this project, we conduct an in-depth analysis of the causes of these effects for policy gradien...

Fair decision making: From learning to predict to learning to decide

Miriam Rateike (Ph.D. Student)

With algorithmic decision making processes being increasingly being deployed in society, there are growing concerns about potential unfairness of these algorithmic systems towards people from certain demographic groups (e.g., gender). To address these concerns, the emerging field of ethical machine learning has prop...

Fast feed-forward video avatars with diffusion prior

David Svitov (Ph.D. Student)

Photo-realistic human avatars are a rapidly developing area of research. However, to the best of my knowledge, all current methods have two shortcomings: Lack of human appearance prior and long training time. These shortcomings limit the applicability of photorealistic human avatars. The drawbacks described above ca...

Feedback models for real-time robotic cloth manipulation

Oriol Barbany (Ph.D. Student)

Object rigidity is still one of the most common assumptions in robotic grasping and manipulation. Nevertheless, many daily life objects like cables, plastics, and clothes present non-negligible deformations. Manipulating garments remains a challenging topic due to the high flexibility of textiles and their nearly in...

Fine grained visual analysis using natural language

Vestéinn Snaebjarnarson (Ph.D. Student)

The project is based around analysis of images by use of natural language, in particular for fine grained categorization and analysis. The idea is that the use of natural language will serve both as grounding for direct labelling as well as for comparison to other sources of information. Adaptation of existing gener...

Foundations of Regularization in Deep Learning

Linara Adilova (Ph.D. Student)

Regularization lies at the core of successful training state-of-the-art deep neural networks. It allows to control overfitting and allows to obtain good generalization even with massively overparametrized models. Regularization influences the training process both implicitly - through the properties of optimizers - ...

Generative modeling and it's theoretical foundations

Simon Damm (Ph.D. Student)

Generative modeling is a fundamental yet complex task in machine and deep learning. This project aims to investigate and broaden our understanding of the theoretical foundations of (deep) generative models. Our interest is twofold. First, we are interested in theoretical properties of the optimization and training d...

Generative Models for Robust Vision

Olaf Dünkel (Ph.D. Student)

Machine learning models are validated and tested on fixed datasets under the assumption of independent and identically distributed samples, which may not fully reflect the models' true capabilities and potential vulnerabilities. These vulnerabilities can become evident when the model is tested in real-world scenario...

Generative models in Geometric Deep Learning

Clément Vignac (Ph.D. Student)

Clément's work focuses on the design of neural architectures for structured data: sets, graphs and point clouds. These problems have in common a large symmetry group, which is the invariance to all possible permutations of the points. In order to design architectures that are both computationally and data efficient,...

Generative/Stochastic/Bayesian Space-Time Neural Networks

Ilze Amanda Auzina (Ph.D. Student)

The PhD project explores the intersection between machine learning and dynamical systems. Throughout the project multiple research directions are investigated. Firstly, the effect of constraining networks with known dynamical properties is researched. Secondly, the project explores dynamical forecasting when the und...

Geometric Deep Learning

Gabriele Cesa (Ph.D. Student)

Many machine learning tasks come with some intrinsic geometric structure. During my PhD, I will study how to encode the geometry of a problem into neural-network architectures to achieve improved data efficiency and generalization. A particular focus will be given to 3D data and the task of 3D reconstruction, where ...

Graph-based Learning from Irregular Spatiotemporal Data

Ivan Marisca (Ph.D. Student)

Irregular spatiotemporal data, characterized by collections of asynchronous observations at different time instants and spatial coordinates, pose a complex challenge in data analysis. These structured data are commonly encountered in sensor networks, such as environmental monitoring networks, traffic management syst...

Hardware-oriented Neural Architecture Search

Luca Robbiano (Ph.D. Student)

Manual neural architecture design is a time-consuming process that requires a massive effort by experts. In the last few years, this led to the development of Neural Architecture Search algorithms, which aim to replace the traditional design approach with more efficient automated methods. This is even more relevant ...

Holistic 3D Scene Understanding for Self-Driving Cars

Zehao Yu (Ph.D. Student)

Holistic 3D scene understanding plays a critical role in self-driving cars. It involves several sub-tasks, such as geometric layout estimation, object detection, recognition, and tracking. While each sub-task may be solved independently, it would be beneficial to utilize the complementary nature of different sub-tas...

Human body motion generation

Mathis Petrovich (Ph.D. Student)

Automatic analysis of people from visual data is of great importance for numerous applications in behavior analysis and prediction, autonomous driving, health care, surveillance, content search, and entertainment. More specifically, analyzing human body dynamics is an essential component of various research directio...

Human Motion Capture and Motion Modeling in Context using Multi-modal Sensing

Andrea Boscolo Camiletto (Ph.D. Student)

In this project, we will explore new ways to reconstruct and model detailed human motion and action in the context of the physical surroundings they happen in. We will explore several research strands in this space. We will explore new types of multi-modal sensing that combine cameras, including body-worn cameras, w...

Human-centric Machine Learning in Healthcare

Nina Corvelo Benz (Ph.D. Student)

With machine learning tools being widely used in social and commerce systems and increasingly also to automate processes in other sectors such as medicine, banking, and employment, machine-made decisions are becoming more and more influential to our everyday life. In many of these real-world applications algorithms’...

Improving Deep Learning Explainability with Interpretable Outputs and Representations

Anders Christensen (Ph.D. Student)

Through recent years it has become abundantly clear how powerful machine learning is. Still, despite the empirical success of deep learning models, there is rarely access to the reasoning behind why a model yields a certain output for some input. Achieving more insight into the decision making of such models and dev...

Independent causal mechanisms in machine learning

Julius von Kügelgen (Ph.D. Student)

Due to changes in environment, measurement device, experimental condition, or sample selection bias, the commonly-made assumption of independent and identically distributed (i.i.d.) random variables underlying many machine learning algorithms is often violated in practice. The perspective of causal modelling offers ...

Interactive AI with a Theory of Mind

Mustafa Mert Çelikok (Ph.D. Student)

In human-AI collaboration, learning a good model of the human is important for an autonomous learning system which aims to help its users in the most efficient way possible. Unfortunately, the data in human-AI interaction is scarce due to the online nature of the tasks. Additional difficulties arise from the bounded...

Interpretable Machine Learning

Jonas Klesen (Ph.D. Student)

Issues around the interpretability of Machine Learning systems are of growing concern. Unfortunately, the research community up until now has failed to converge on established methods for arriving at powerful yet interpretable models. Even worse, and as opposed to similar desiderata of Machine Learning s...

Interpretable ML for stress forecasting and management

Batuhan Koyuncu (Ph.D. Student)

Modeling temporal stress patterns of people is a challenging task since stress patterns are complex and have a heterogeneous nature. However, it is a crucial task for forecasting and mitigating stress. The objectives of this Ph.D. project are understanding stress causes, forecasting stress levels over time, and prov...

Interpretable uncertainty in NLP systems using human uncertainty

Joris Baan (Ph.D. Student)

Accurate and reliable representations of uncertainty are crucial in trustworthy NLP systems. For example, to pass uncertain predictions on to human experts or convey uncertainty to users to help them interpret predictions. However, it is not straightforward to evaluate uncertainty, partly because uncertainty is rare...

Intrinisic structural properties of neural networks and their effect on generalization

Sidak Pal Singh (Ph.D. Student)

The main aim of this doctoral thesis is to better understand the properties and mechanisms underlying the success of deep neural networks. In particular, our emphasis is on identifying relevant structural properties of neural networks that are inherently at play and then utilize them to holistically investigate the ...

Invariance and Causality in Machine Learning

Cian Eastwood (Ph.D. Student)

Machine learning (ML) methods have achieved remarkable successes on problems with independent and identically-distributed (IID) data. However, real-world data is not IID—environments change, experimental conditions shift, and new measurement devices are used. Current ML methods struggle when asked to transfer or ada...

Irrational Human Behaviour and AI

Aditya Gulati (Ph.D. Student)

Humans have been known to exhibit irrational behaviour in many situations. Our current AI systems however, are not well equipped to deal with or understand these types of behaviour. Our goal is to build an understanding of these irrational behaviours into our AI systems in order to design tools that can help us make...

Large generative vision models for content creation and representation learning

Saman Motamed (Ph.D. Student)

l'm broadly interested in Generative Vision models for content creation and representation learning. My research falls in to the following two categories: 1) I aim to gain a better understanding of how to enable user-intuitive control over generative models for personalized content creation with limited data. This i...

Learning cloth handling skills with Gaussian Processes and Model Predictive Control

Edoardo Caldarelli (Ph.D. Student)

Robot learning of cloth handling skills is an increasingly relevant task, that arises in the field of assistive robotics. However, it presents numerous challenges, related both to the non-rigid nature of the object to be manipulated, and to the type of real-world datasets used to learn these skills, which usually co...

Learning Curricula in Open-Ended Worlds

Minqi Jiang (Ph.D. Student)

Adaptive curricula have played a pivotal role in successfully applying deep reinforcement learning (RL) to the most challenging domains. By presenting RL agents with variations of the external world that best challenge their present capabilities, adaptive curricula can greatly improve how quickly agents learn,...

Learning from distributions with kernelized optimal transport

Dimitri Meunier (Ph.D. Student)

The problem of learning functions over spaces of probabilities -- or distribution regression -- is gaining significant interest in the machine learning community. A key challenge behind this problem is to identify a suitable representation capturing all relevant properties of the underlying functional mapping. A pri...

Learning Meaningful Object Representations

Frederik Nolte (Ph.D. Student)

A fundamental aspect of human cognition is interpreting their surrounding environment as a collection of objects and the relations among them. What an object means to us is not only characterised by its physical properties, but crucially entails its affordances, informing us what kind of actions can be executed on a...

Learning of hidden principled mechanisms behind data without supervision

Takeru Miyato (Ph.D. Student)

In the past, various neural networks models have been developed based on the in-distribution performance on benchmark datasets like ImageNet. However, in many cases, the data in real applications differs from the dataset on which the model was trained because of the change in the mechanisms behind the dataset. In or...

Learning real-world perception in simulations

Xu Chen (Ph.D. Student)

The difficulty of acquiring annotated real-world data has limited the applicability of deep learning in many computer vision tasks. As one way to overcome this limitation, training deep networks with synthetic images from simulation has demonstrated its potential. However, current simulations still lack diversity an...

Learning Stocastic Dynamical Systems

Erfan Mirzaei (Ph.D. Student)

Dynamical systems are mathematical models used to describe the evolution of state variables over time. These models, often represented by nonlinear differential equations (ordinary or partial), and possibly stochastic, have wide-ranging applications in science and engineering. This project aims to investigate data-d...

Learning to solve multiple-view geometry

Diana Sungatullina (Ph.D. Student)

Multi-view geometry is an important field in computer vision and robotics, which provides an understanding to the foundations of the subject. The development of this field has, however, not yet been greatly influenced by the recent advances in machine learning and geometrical machine learning in particular. We aim a...

Learning-based 3D Approach for Egocentric Vision

Weirong Chen (Ph.D. Student)

Egocentric vision, which involves understanding and interpreting visual data from a first-person perspective, is crucial for various applications, including augmented reality, robotics, and assistive technologies. This project seeks to advance the current state of visual foundation models while addressing challenges...

lmproving Image Synthesis and Manipulation Control with GANs

Edgar Schönfeld (Ph.D. Student)

Among the major challenges of generative adversarial networks (GANs) remain the ability to create images that are indistinguishable from real images and the ability to depict precisely the content specified by the user. To this end, this work proposes methods to improve synthesis quality and maximize control over th...

Machine Learning and Causal Inference to Optimize Genomic Interventions using Disease State Representations

Bowen Fan (Ph.D. Student)

The human genome contains a torrent of information that gives clues not only about human origin, evolution, biological function, but also diseases. The goal of my project aims at developing novel machine learning techniques to better understand the complex genomic data and also other forms of data that can represent...

Machine Learning for Biological Network Analysis

Giulia Muzio (Ph.D. Student)

The main objective of my project is to develop methods for network-based genome-wide association studies (GWAS) that combine computational efficiency, statistical power and interpretability, thereby enabling the discovery of biological pathways underlying complex phenotypic traits. GWAS aim to identify statistical ...

Machine Learning for Single-Cell Omics

Merel Kuijs (Ph.D. Student)

In spite of the massive effort in ensuring drug safety and efficacy, some drugs fail to achieve a therapeutic effect and others have severe side effects. A personalized approach to medicine is needed to maximize every patient’s chance of recovery and relieve pressure on healthcare systems, but data to inform precisi...

Machine Learning for the Fusion of Remote Sensing and Tweets Data for Green Space Analysis

Mohamed Ibrahim (Ph.D. Student)

There is increasing evidence that people with higher access to urban green spaces have better mental health and well-being. This project aims to examine the impact of urban green spaces on mental health, and what features play the biggest role. The combination of airborne or space-borne remote sensing images and geo...

Mathematical aspects of variational quantum machine learning models

Elies Gil-Fuster (Ph.D. Student)

Recent years have seen the birth and growth of quantum machine learning, a new discipline which uses quantum computers for data analysis. Within this field, many heuristics have been proposed and to some extent individually tested. Yet, there is no truly holistic framework to study and characterize the essence and q...

Methods for Robust Feature Learning

Sindy Löwe (Ph.D. Student)

The representation of objects and their relations lies at the center of our ability to reason and to adapt to new environments. In my PhD, I want to develop algorithms that learn object-centric representations from low-level perceptual inputs in an unsupervised fashion.

Modeling Humans in the Scene with Compositional and Controllable Neural Representations

Zijian Dong (Ph.D. Student)

This project aims to develop generative 3D models for controllable 3D synthetic humans in a scene. The first part of the project is to generate one animatable neural human avatars given only a few RGB/RGBD images of a person from different views. The second part of the project is to represent a scene with compositio...

Modeling the molecular response of single cells to drug perturbations

Artur Szalata (Ph.D. Student)

Biological single-cell sequencing data can be used to learn about cellular phenotypes, developmental trajectories, and disease. It is increasingly utilized to measure a cell's molecular state across perturbations. To better understand a cellular system, we develop a machine learning model that can accurately predict...

Modular Language and Domain Adaptation of Language Models

Indraneil Paul (Ph.D. Student)

This project aims to mitigate model development and maintenance costs at all points along its lifecycle by improving modularity. We seek to improve efficiency using modular additions to the network and do so effectively in a manner that does not incur the cost of catastrophic interference. Such methods can, in time,...

Multi-modal Continual Learning

Vishaal Udandarao (Ph.D. Student)

The ability to learn continually across a diverse set of tasks and domains is an important fundamental problem in machine learning. Continual learning has emerged to be a pivotal research area in which systems are trained on diverse downstream tasks sequentially, while performing well on all the tasks equally. Most ...

Multi-Task Learning for Medical Image Analysis and Data Mining

Jiayi Shen (Ph.D. Student)