PhD & Postdoc Program
The ELLIS PhD & Postdoc Program supports excellent young researchers by connecting them to leading researchers across Europe and offering a variety of networking and training activities, including summer schools and workshops. ELLIS PhDs and postdocs conduct cutting-edge curiosity-driven research in machine learning or a related research area with the goal of publishing in top-tier conferences in the field.
Tracks
There are two tracks within the ELLIS PhD & Postdoc Program: the academic track and the industry track. These tracks have separate requirements for admission and criteria for activity during the appointment, but otherwise offer the same benefits, network and resources to the applicant.
Academic track
PhD students and postdocs in the academic track strive for international collaboration as they partner with two European academic institutions in their research. These candidates are supervised by two advisors from different European countries: one of the advisors must be an ELLIS fellow/scholar or unit faculty; the other advisor should be an ELLIS fellow, scholar, unit faculty or member. PhDs and postdocs in the program visit the exchange institution for min. 6 months (the partitioning of this time is flexible). Normally, the exchange is partially sponsored by the exchange institution; ELLIS PhD students and postdocs are also eligible to apply for the ELISE mobility grant.
Industry track
The industry track is open to PhD and postdoc candidates that will be part of a collaboration between an academic institution and an industry partner, and will spend time conducting research at the industry partner during their PhD or postdoc. The candidate will spend a minimum of 50% of their time at the academic institution, and at least 6 months (cumulative) with the industry partner.
For this track, both advisors may be located in the same country. One advisor will represent the academic institution and the other the industry partner. One advisor must be an ELLIS fellow/scholar or unit faculty. The second advisor can be an ELLIS fellow, scholar, member, unit faculty OR it is also possible for the second advisor to join if they have co-authored a paper with the applying student as a result of their collaboration, in a top-tier venue in machine learning or related sub-fields (details here).
How to join ELLIS as a PhD or postdoc
There are two ways to become an ELLIS PhD student or postdoc: (1) via our central application process (if you want to start a PhD with one of the ELLIS fellows/scholars or unit faculty); (2) via a nomination process (if you’re already working with one of the ELLIS fellows/scholars or unit faculty as a PhD or postdoc). Admission to the program is competitive.
1. Central application
Prospective students may apply through the central ELLIS application portal to become a PhD student within the ELLIS network (deadline once a year in November). In their application, applicants choose from a set of ELLIS research areas and indicate preferences for ELLIS fellows, scholars or unit faculty they would like to work with. Candidates will be centrally reviewed for excellence by a pool of experts; the best candidates will be eligible for the ELLIS program and may be invited for interviews by individual advisors. If an offer is made, an agreement is signed which specifies the main supervisor, the co-supervisor, the funding as well as the exchange and graduation plan. Students will be funded through the advisor’s resources and get their degree from the home institution. Please read our FAQs and slides for more information.
Currently, the central application process is only for new PhD students. Postdocs are only recruited non-centrally via the nomination process described in 2.
Calls and admissions: There is a yearly central call for applications in fall, which will be announced on the ELLIS website. Admission to the program is competitive. For reference, about 5-10% of eligible applicants are accepted via the central call. The next chance to apply via the central recruiting is in fall 2022. Nomination to the program (for students who already started their PhD with ELLIS faculty) is possible year-round (see 2).
2. Nomination
ELLIS fellows, scholars or unit faculty may nominate PhD students or postdocs who are working with them to become ELLIS PhD students or postdocs in the academic or industry track. Note that postdocs of either track are currently only recruited via nomination. Please see this page for more details about the requirements and the nomination process.
More Information
Click here to download a slide deck with more details about the ELLIS PhD and Postdoc Program.
Contact: phd@ellis.eu (general questions, central recruiting, academic track) | phd-industry@ellis.eu (industry track)
The ELLIS PhD and Postdoc Program is supported by the European Union’s Horizon 2020 research and innovation programme under ELISE Grant Agreement No. 951847.
- PhD & Postdoc Coordinator (Academia)
- PhD & Postdoc Coordinator (Industry)
- PhD & Postdoc Assistant (Academia)
- Web Developer
Adaptation and Robustness in Brains and Machines
Steffen Schneider (Ph.D. Student)
Understanding the mechanisms underlying robust learning and efficient adaptation is an open problem both in neuroscience and machine learning. While robustness and domain adaptation in ML is commonly studied with computer vision tasks, adaptation research in neuroscience has been traditionally carried out in sensori...
| Primary Host: | Matthias Bethge (University of Tübingen) |
| Exchange Host: | Mackenzie Mathis (EPFL & Harvard University) |
| PhD Duration: | 01 November 2019 - 31 October 2022 |
| Exchange Duration: | 18 February 2020 - 31 March 2020 01 January 2021 - 31 January 2022 |
Multitask Visual Representation Learning
Duy-Kien Nguyen (Ph.D. Student)
In order to build a comprehensive vision system at the human level, it is necessary for the system to be able to deal with multiple problems at different levels. Previously, researchers have focused on individual tasks separately with a specific network architecture design and many hand-crafted modules, which makes ...
| Primary Advisor: | Cees Snoek (University of Amsterdam) |
| Industry Advisor: | Olaf Booij (TOMTOM) |
| PhD Duration: | 19 October 2020 - 19 October 2024 |
3D Human Pose Estimation
Nadine Rüegg (Ph.D. Student)
I'm working at the intersection between Computer Vision and Machine Learning. Specifically, I focus on 3D human shape and pose estimation and have strong interests in unsupervised learning. I aim to find a good balance between labeling effort and performance.
| Primary Host: | Konrad Schindler (ETH Zürich) |
| Exchange Host: | Michael J. Black (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 June 2017 - 01 June 2022 |
| Exchange Duration: | 01 June 2018 - 01 June 2019 |
3D Vision Meets Deep Learning
Songyou Peng (Ph.D. Student)
My research interests lie at the intersection of deep learning and computer vision, especially 3D vision. What could be the optimal 3D representation? How to effectively and efficiently combine deep learning with 3D vision tasks? How to tackle multiple 3D tasks together with less or no supervision? During the period...
| Primary Host: | Marc Pollefeys (ETH Zürich & Microsoft) |
| Exchange Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 September 2019 - Ongoing |
| Exchange Duration: | 01 June 2020 - 01 June 2021 |
A game theoretic framework for reinforcement learning and imitation learning
Luca Viano (Ph.D. Student)
Reinforcement Learning and Imitation Learning achieved impressive empirical results in recent years. Still, little is known about the theoretical properties of commonly used algorithms. This PhD project aims to use insights from the field of game theory and optimization to develop algorithms with mathematical guaran...
| Primary Host: | Volkan Cevher (EPFL) |
| Exchange Host: | Gergely Neu (Universitat Pompeu Fabra) |
| PhD Duration: | 01 September 2021 - 01 September 2025 |
| Exchange Duration: | 01 March 2023 - 01 September 2023 |
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...
| Primary Host: | Pascal Frossard (EPFL) |
| Exchange Host: | Philip H. S. Torr (University of Oxford) |
| PhD Duration: | 01 November 2018 - 01 May 2023 |
| Exchange Duration: | 01 January 2022 - 30 June 2022 |
Accountability for AI
Florian Dorner (Ph.D. Student)
With the more and more widespread deployment of Al systems in the real world, they are likely going to have larger and larger impacts on society, including accidents, political destabilization and other negative externalities. To increase developers' accountability for negative societal impacts of their Al systems, ...
| Primary Host: | Moritz Hardt (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Fanny Yang (ETH Zürich) |
| PhD Duration: | 10 October 2022 - 10 October 2025 |
| Exchange Duration: | 01 April 2024 - 01 April 2025 |
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...
| Primary Host: | Nuria Oliver (DataPop Alliance, Vodafone Institute & The Spanish Royal Academy of Engineering) |
| Exchange Host: | Manuel Gomez Rodriguez (Max Planck Institute for Software Systems) |
| PhD Duration: | 01 November 2021 - 01 November 2024 |
| Exchange Duration: | - Ongoing |
Advancing SLAM through Deep Learning
Niclas Vödisch (Ph.D. Student)
A fundamental challenge in the field of mobile robotics is to determine the robot’s pose relative to its environment. Commonly, this is achieved by employing simultaneous localization and mapping (SLAM) systems. While classical methods are well studied and provide reliable solutions to the localization problem, how ...
| Primary Host: | Wolfram Burgard (University of Freiburg) |
| Exchange Host: | Davide Scaramuzza (ETH & University of Zürich) |
| PhD Duration: | 01 June 2021 - 31 May 2025 |
| Exchange Duration: | 01 June 2023 - 30 November 2023 |
AI Fairness in Federated Learning
Gergely Dániel Németh (Ph.D. Student)
Federated Learning is a rapidly emerging approach to solve privacy problems regarding Machine Learning applications. Fairness in Artificial Intelligence is also a field that gained awareness in recent years. At the intersection of the two fields, we can find new solutions for problems that exist in centralized machi...
| Primary Host: | Nuria Oliver (DataPop Alliance, Vodafone Institute & The Spanish Royal Academy of Engineering) |
| Exchange Host: | Novi Quadrianto (University of Sussex) |
| PhD Duration: | 01 November 2021 - 31 July 2024 |
| Exchange Duration: | 01 January 2023 - 30 June 2023 |
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...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | José Miguel Hernández-Lobato (University of Cambridge) |
| PhD Duration: | 01 January 2020 - Ongoing |
| Exchange Duration: | 01 January 2020 - 31 December 2020 |
Attention-guided cross domain visual geo-localization
Gabriele Trivigno (Ph.D. Student)
Photo geolocation is a challenging task since many photos offer only few cues about their location. For instance, an image of a beach could be taken on many coasts across the world. Even when landmarks are present there can still be ambiguity: a photo of the Rialto Bridge could be taken either at its original locat...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Torsten Sattler (Czech Technical University) |
| PhD Duration: | 01 November 2021 - 01 November 2024 |
| Exchange Duration: | 01 February 2024 - Ongoing 01 August 2024 - Ongoing |
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...
| Primary Host: | Tatiana Tommasi (Politecnico di Torino) |
| Exchange Host: | Jan Peters (Technical University of Darmstadt & Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 November 2021 - 31 October 2024 |
| Exchange Duration: | 01 January 2023 - 01 July 2023 |
Automated Synthesis of Counterfactual Interventions for Explainable and Fair Machine Learning
Giovanni De Toni (Ph.D. Student)
As humans, we make countless decisions every day in many different areas of our lives. Recently, state-of-the-art machine learning models have been used to build automated decision-making systems to enhance human judgment, ranging from accepting or rejecting a job applicant to prescribing medications and treatments....
| Primary Host: | Bruno Lepri (FBK & MIT Media Lab) |
| Exchange Host: | Manuel Gomez Rodriguez (Max Planck Institute for Software Systems) |
| PhD Duration: | 01 October 2021 - 31 October 2025 |
| Exchange Duration: | 01 January 2023 - 01 June 2023 |
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...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Carlo Ciliberto (University College London) |
| PostDoc Duration: | 01 June 2021 - 31 May 2023 |
| Exchange Duration: | 01 February 2022 - 01 August 2022 |
Building the mathematical structure of symmetries and causality into neural networks
Pim de Haan (Ph.D. Student)
A growing consensus in the field is that many machine learning problems possess symmetries and that neural networks that respect those symmetries – are equivariant – outperform models that are not. The goal of the PhD project is to generalize the used mathematical toolkit of groups and representations to more genera...
| Primary Advisor: | Max Welling (University of Amsterdam) |
| Industry Advisor: | Taco Cohen (Qualcomm AI Research) |
| PhD Duration: | 01 April 2019 - 01 April 2023 |
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...
| Primary Host: | Matthias Bethge (University of Tübingen) |
| Exchange Host: | Ferenc Huszár (University of Cambridge) |
| PhD Duration: | 01 April 2021 - 31 March 2024 |
| Exchange Duration: | 01 September 2022 - 28 February 2023 |
Causal Representations for Reinforcement Learning
Yashas Annadani (Ph.D. Student)
Systematic generalisation beyond the independent and identically distributed (IID) setting is crucial for learning agents interacting with the environment in the real-world. Improvements with regards to generalisation has been seen in supervised learning with large language and vision models and out-of-distribution ...
| Primary Host: | Stefan Bauer (KTH Royal Institute of Technology) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2021 - 30 September 2025 |
| Exchange Duration: | 01 October 2021 - 31 March 2022 |
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...
| Primary Advisor: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Industry Advisor: | Dominik Janzing (Amazon Research Tübingen) |
| PhD Duration: | 01 December 2021 - 01 December 2024 |
Causality of Enhanced Model Interpretability
Amir-Hossein Karimi (Ph.D. Student)
As machine learning is increasingly used to inform decision-making in consequential real-world settings (e.g., pre-trial bail, loan approval, or prescribing life-altering medication), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. My ...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Thomas Hofmann (ETH Zürich) |
| PhD Duration: | 01 October 2018 - 31 December 2022 |
| Exchange Duration: | 01 September 2020 - 31 August 2021 |
Combining Probabilistic Inference and Deep Learning
James Urquhart Allingham (Ph.D. Student)
Deep learning is an extremely successful machine learning paradigm that has been the driving force behind the renewed excitement around machine learning over the last seven or so years since AlexNet won the ImageNet LSVRC competition. However, despite the successes of deep learning, it is not without its flaws. One ...
| Primary Host: | José Miguel Hernández-Lobato (University of Cambridge) |
| Exchange Host: | Eric Nalisnick (University of Amsterdam) |
| PhD Duration: | 01 October 2019 - 30 April 2023 |
| Exchange Duration: | 01 February 2022 - 31 July 2022 |
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...
| Primary Host: | Kristel Van Steen (University of Liège & KU Leuven) |
| Exchange Host: | Karsten Borgwardt (ETH Zürich) |
| PhD Duration: | 15 March 2019 - 15 March 2022 |
| Exchange Duration: | 01 February 2021 - 30 April 2021 |
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 ...
| Primary Advisor: | Cees Snoek (University of Amsterdam) |
| Industry Advisor: | Xiantong Zhen (University of Amsterdam & Inception Institute of Artificial Intelligence) |
| PhD Duration: | 01 January 2020 - 31 December 2023 |
Continual Learning in Computer Vision
Sebastian Dziadzio (Ph.D. Student)
The dominant deep learning setting involves training a model offline on a fixed dataset before deploying it in the real world. Implicit in this approach is an important and restrictive assumption: both the training data and future inputs are assumed to be IID samples from a single stationary distribution. In reality...
| Primary Host: | Matthias Bethge (University of Tübingen) |
| Exchange Host: | Tinne Tuytelaars (KU Leuven) |
| PhD Duration: | 01 February 2022 - 31 January 2025 |
| Exchange Duration: | 01 April 2023 - 01 October 2023 |
Continual Open-set Object Detection
Yaoyao Liu (Ph.D. Student)
Most object detection methods require abundant labeled training samples per category. However, we often receive a continuous temporal stream of visual data with many unknown categories in real-world applications. For example, a robotic learning system needs to deal with new objects observed in the environments but c...
| Primary Host: | Bernt Schiele (Max Planck Institute for Informatics & Saarland University) |
| Exchange Host: | Christian Rupprecht (University of Oxford) |
| PhD Duration: | 01 February 2020 - 01 July 2023 |
| Exchange Duration: | 15 July 2022 - 15 January 2023 |
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...
| Primary Advisor: | Sepp Hochreiter (Johannes Kepler University Linz) |
| Industry Advisor: | Razvan Pascanu (Google DeepMind) |
| PhD Duration: | 01 February 2022 - 31 January 2025 |
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 ...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Bernhard Nessler (Johannes Kepler University Linz) |
| PhD Duration: | 01 October 2021 - 01 October 2024 |
| Exchange Duration: | 01 February 2024 - 01 August 2024 |
Cross-Domain 3D Visual Learning
Antonio Alliegro (Ph.D. Student)
Depth cameras and LiDAR sensors are important tools for agents that need to perceive the world and interact with it, thus 3D data managing and learning algorithms are quickly becoming essential. Deep learning has achieved a significant leap for 2D computer vision, and for 3D applications is currently demonstrating g...
| Primary Host: | Tatiana Tommasi (Politecnico di Torino) |
| Exchange Host: | Matthias Nießner (Technical University of Munich) |
| PhD Duration: | 01 November 2020 - 31 October 2023 |
| Exchange Duration: | 01 July 2022 - 31 December 2022 |
Dynamically Evolving Deep Architectures
Rupert Mitchell (Ph.D. Student)
My research focuses on the modification of deep architectures live during training. In contrast to the relatively well explored area of the pure removal of parts of an architecture (i.e. pruning), I am particularly interested in combining this with the addition of parts as well, for example increasing the width or d...
| Primary Host: | Kristian Kersting (Technical University of Darmstadt) |
| Exchange Host: | Ole Winther (University of Copenhagen & Technical University of Denmark) |
| PhD Duration: | 08 September 2021 - 07 September 2024 |
| Exchange Duration: | - Ongoing |
Efficient Deep Learning for Sets
David Zhang (Ph.D. Student)
Sets help us organize our understanding of the real world: complex images can be simplified as sets of objects, arbitrary 3D shapes can be described by sets of coordinates, and graphs (a tuple of two sets) can model all relational structures between objects. My research focuses on inferring sets with deep learning a...
| Primary Advisor: | Cees Snoek (University of Amsterdam) |
| Industry Advisor: | Gertjan Burghouts (TNO) |
| PhD Duration: | 01 April 2019 - 31 March 2023 |
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....
| Primary Host: | Devis Tuia (EPFL) |
| Exchange Host: | Zeynep Akata (University of Tübingen) |
| PostDoc Duration: | 01 February 2019 - 31 January 2023 |
| Exchange Duration: | 01 August 2020 - 31 October 2020 |
Explainable Multimodal Representation Learning
Karsten Roth (Ph.D. Student)
Human perception, but also interaction, is inherently multimodal, i.e. visual and audio information get processed together and the emerging knowledge is communicated through some form of language. In this project, our aim is to learn multimodal representations using artificial neural networks. Our application domain...
| Primary Host: | Zeynep Akata (University of Tübingen) |
| Exchange Host: | Oriol Vinyals (Google DeepMind) |
| PhD Duration: | 15 May 2021 - 31 December 2024 |
| Exchange Duration: | 15 May 2024 - 31 December 2024 |
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...
| Primary Host: | Isabel Valera (Saarland University & Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Max Welling (University of Amsterdam) |
| PhD Duration: | 15 July 2020 - 14 July 2023 |
| Exchange Duration: | 01 June 2022 - 31 December 2022 |
Federated Semantic Segmentation architectures on IoT devices using Neural Architecture Search
Shyam Nandan Rai (Ph.D. Student)
Scene understanding is one of the key components for robotic navigation and self-driving application. Semantic segmentation gives detailed information about a scene as it involves pixel-wise dense labeling. However, semantic segmentation models are challenging to deploy on resource constraint devices due to high com...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Zeynep Akata (University of Tübingen) |
| PhD Duration: | 01 November 2021 - 31 October 2024 |
| Exchange Duration: | 01 February 2024 - 31 October 2024 |
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...
| Primary Host: | Carme Torras (Universitat Politècnica de Catalunya) |
| Exchange Host: | Amir Zamir (EPFL) |
| PhD Duration: | 01 July 2021 - 31 May 2024 |
| Exchange Duration: | 01 January 2023 - 31 May 2023 |
Few-shot Learning with Pretrained Language Models
Abdullatif Köksal (Ph.D. Student)
Large pretrained language models (PLMs) perform well on many NLP tasks without supervised training. This phenomenon is best demonstrated in GPT-3 by its translation capability from different languages to English with just 64 contextual examples. On the other hand, contextual examples enable PLMs to work with multipl...
| Primary Host: | Hinrich Schütze (LMU Munich) |
| Exchange Host: | Anna Korhonen (University of Cambridge) |
| PhD Duration: | 01 January 2022 - 01 January 2025 |
| Exchange Duration: | 01 January 2024 - 01 July 2024 |
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 - ...
| Primary Host: | Asja Fischer (Ruhr University Bochum) |
| Exchange Host: | Martin Jaggi (EPFL) |
| PhD Duration: | 01 February 2021 - 31 March 2024 |
| Exchange Duration: | 01 June 2022 - 31 December 2022 |
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...
| Primary Host: | Asja Fischer (Ruhr University Bochum) |
| Exchange Host: | Arthur Gretton (University College London) |
| PhD Duration: | 01 July 2021 - 30 June 2024 |
| Exchange Duration: | 01 June 2022 - 31 August 2022 01 June 2023 - 31 August 2023 |
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,...
| Primary Host: | Pascal Frossard (EPFL) |
| Exchange Host: | Max Welling (University of Amsterdam) |
| PhD Duration: | 01 November 2019 - 03 May 2023 |
| Exchange Duration: | 01 September 2021 - 31 December 2021 01 June 2022 - 31 July 2022 |
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 ...
| Primary Advisor: | Max Welling (University of Amsterdam) |
| Industry Advisor: | Taco Cohen (Qualcomm AI Research) |
| PhD Duration: | 01 September 2019 - 30 September 2023 |
Grounding symbols in observations via causal, object centric world-models
Anson Lei (Ph.D. Student)
Symbol grounding is a key part of classical AI and harbours significant potential in the ability to perform symbolic and causal reasoning on real-world data. In contrast, machine learning currently operates on raw sensor data and typically without consideration of any symbolic structure in the data. The recent emerg...
| Primary Host: | Ingmar Posner (University of Oxford) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2021 - 30 April 2026 |
| Exchange Duration: | - Ongoing |
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 ...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Fabio Maria Carlucci (Facebook) |
| PhD Duration: | 01 November 2021 - 31 October 2024 |
| Exchange Duration: | 01 February 2024 - 31 August 2024 |
Harmonic Analysis for Stochastic Neural Networks
Adeel Pervez (Ph.D. Student)
In this work we explore harmonic analytic techniques to improve the learning capabilities of stochastic neural network models. Stochastic neural networks are widely used in probabilistic modeling for unsupervised and representation learning. Such models are often limited by problems of instability and by the type of...
| Primary Advisor: | Efstratios Gavves (University of Amsterdam) |
| Industry Advisor: | Taco Cohen (Qualcomm AI Research) |
| PhD Duration: | 01 February 2019 - 31 January 2023 |
Holistic 3D Scene Reconstruction
Baris Can Cam (Ph.D. Student)
The main aim of this project is to build a holistic model for 3D scene reconstruction. Despite 3D scene reconstruction having been a popular sub-field in computer vision and computer graphics, the majority of previous work focuses only on geometric reconstruction. However, human-level understanding of a dynamic scen...
| Primary Host: | Stefan Roth (Technical University of Darmstadt) |
| Exchange Host: | Otmar Hilliges (ETH Zürich) |
| PhD Duration: | 15 November 2021 - 14 November 2025 |
| Exchange Duration: | 15 November 2022 - 14 November 2023 |
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...
| Primary Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Torsten Sattler (Czech Technical University) |
| PhD Duration: | 01 September 2021 - 30 June 2025 |
| Exchange Duration: | 01 December 2022 - 31 May 2023 |
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...
| Primary Host: | Gül Varol (École des Ponts ParisTech) |
| Exchange Host: | Michael J. Black (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2020 - 30 September 2023 |
| Exchange Duration: | 01 April 2022 - 30 September 2023 |
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’...
| Primary Host: | Manuel Gomez Rodriguez (Max Planck Institute for Software Systems) |
| Exchange Host: | Karsten Borgwardt (ETH Zürich) |
| PhD Duration: | 01 June 2021 - 30 June 2025 |
| Exchange Duration: | 01 January 2023 - 30 June 2023 |
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...
| Primary Host: | Ole Winther (University of Copenhagen & Technical University of Denmark) |
| Exchange Host: | Zeynep Akata (University of Tübingen) |
| PhD Duration: | 01 December 2021 - 30 November 2024 |
| Exchange Duration: | 01 September 2022 - 31 August 2023 |
Incremental Learning in Semantic Segmentation
Fabio Cermelli (Ph.D. Student)
Semantic Segmentation is a crucial task in computer vision that consists of predicting for each pixel of an image its semantic meaning, i.e. pixel-wise classification. This task is crucial for many applications, ranging from self-driving cars to autonomous manufacturing. In the last years, thanks to the rise of deep...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Matthieu Cord (Sorbonne University) |
| PhD Duration: | 01 November 2019 - 31 January 2023 |
| Exchange Duration: | 15 March 2022 - 15 September 2022 |
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 ...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Adrian Weller (University of Cambridge & The Alan Turing Institute) |
| PhD Duration: | 01 September 2018 - 28 February 2023 |
| Exchange Duration: | 01 September 2018 - 31 August 2019 |
Independent Component Analysis: linear and nonlinear, single and multi-view. Identifiability and estimation algorithms
Luigi Gresele (Ph.D. Student)
Independent Component Analysis (ICA) provides a principled framework for unsupervised feature extraction and blind source separation, with ubiquitous applications in signal processing, astronomy and neuroimaging. In the multi-view setting, the aim is to extract common sources of variability from multiple related obs...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Aapo Hyvärinen (University of Helsinki) |
| PhD Duration: | 01 October 2017 - Ongoing |
| Exchange Duration: | 01 October 2019 - 31 December 2019 |
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...
| Primary Host: | Samuel Kaski (Aalto University, Finnish Centre for AI & University of Manchester) |
| Exchange Host: | Frans A. Oliehoek (Delft University of Technology) |
| PhD Duration: | 01 February 2019 - 01 February 2023 |
| Exchange Duration: | 15 September 2020 - 15 March 2021 |
Interactive Multimodal Learning
Haau-Sing Li (Ph.D. Student)
Multimodal learning contains a set of challenging tasks. It requires a deep understanding of all relevant modalities (language, vision, software program) and of the relationships between them. Furthermore, the lack of high-quality datasets increases the difficulty of related tasks. In this project, we will work with...
| Primary Host: | Iryna Gurevych (Technical University of Darmstadt) |
| Exchange Host: | André Martins (University of Lisbon) |
| PhD Duration: | 01 July 2021 - 30 June 2025 |
| Exchange Duration: | 01 July 2023 - 30 June 2024 |
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...
| Primary Host: | Isabel Valera (Saarland University & Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Novi Quadrianto (University of Sussex) |
| PhD Duration: | 01 September 2021 - 01 September 2024 |
| Exchange Duration: | - Ongoing |
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...
| Primary Host: | Isabel Valera (Saarland University & Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Ole Winther (University of Copenhagen & Technical University of Denmark) |
| PhD Duration: | 20 September 2021 - Ongoing |
| Exchange Duration: | - Ongoing |
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 ...
| Primary Host: | Thomas Hofmann (ETH Zürich) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 September 2020 - 31 August 2024 |
| Exchange Duration: | 01 September 2021 - 31 August 2022 |
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...
| Primary Host: | Chris Williams (University of Edinburgh & The Alan Turing Institute) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 September 2018 - 30 September 2022 |
| Exchange Duration: | 01 April 2021 - 28 February 2022 |
Investigating and preventing harmful cultural implications of AI in social media
Piera Riccio (Ph.D. Student)
Social media platforms are reshaping the flow of information in our society, establishing new paradigms of mass communication. Because of their ubiquitous nature, they constantly influence our daily choices, having a widespread impact on different facets of our culture. On such platforms, AI algorithms are massively...
| Primary Host: | Nuria Oliver (DataPop Alliance, Vodafone Institute & The Spanish Royal Academy of Engineering) |
| Exchange Host: | Thomas Hofmann (ETH Zürich) |
| PhD Duration: | 01 November 2021 - 01 November 2024 |
| Exchange Duration: | - Ongoing |
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...
| Primary Host: | Nuria Oliver (DataPop Alliance, Vodafone Institute & The Spanish Royal Academy of Engineering) |
| Exchange Host: | Bruno Lepri (FBK & MIT Media Lab) |
| PhD Duration: | 01 December 2021 - 31 December 2025 |
| Exchange Duration: | - Ongoing |
Joint Sentence and Word Alignment
Peiqin Lin (Ph.D. Student)
Word alignment is generally decomposed into two subproblems: first align sentences, then align words on the assumption that only words in aligned sentences can be aligned. This decomposition works well for many genres of parallel corpora, in particular, for parliamentary proceedings and for legal and business text. ...
| Primary Host: | Hinrich Schütze (LMU Munich) |
| Exchange Host: | André Martins (University of Lisbon) |
| PhD Duration: | 01 October 2021 - 30 September 2024 |
| Exchange Duration: | 01 October 2022 - 31 March 2023 |
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...
| Primary Host: | Carme Torras (Universitat Politècnica de Catalunya) |
| Exchange Host: | Lorenzo Rosasco (University of Genoa, Italian Institute of Technology & Massachusetts Institute of Technology) |
| PhD Duration: | 16 June 2021 - 16 June 2024 |
| Exchange Duration: | 01 June 2022 - 01 December 2022 |
Learning compact and efficient feature representations
Zhuo Su (Ph.D. Student)
Energy efficient sensing and computing is vital at all levels, from the smallest sensor like the chip to ultra high performance processors and systems like the cloud, especially in the post Moore's Law era. Energy efficient AI enables AI to move beyond the cloud and to reach the edge, which is critical to the progre...
| Primary Host: | Li Liu (University of Oulu) |
| Exchange Host: | Max Welling (University of Amsterdam) |
| PhD Duration: | 01 October 2018 - 31 December 2022 |
| Exchange Duration: | 01 October 2021 - 31 March 2022 |
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,...
| Primary Advisor: | Laura Toni (University College London) |
| Industry Advisor: | Tim Rocktäschel (University College London & Meta AI) |
| PhD Duration: | 01 April 2022 - 01 October 2023 |
Learning from multiple distributions
Maximilian Beck (Ph.D. Student)
Traditional deep learning methods perform well in single-domain settings where a vast amount of data is available, but fail in applications where labeled data is limited and comes from different domains. This is for example the case when industrial sensor systems need adjustments to new operating conditions or when ...
| Primary Host: | Sepp Hochreiter (Johannes Kepler University Linz) |
| Exchange Host: | Gerhard Neumann (Karlsruhe Institute of Technology) |
| PhD Duration: | 01 July 2021 - Ongoing |
| Exchange Duration: | 01 February 2024 - 01 August 2024 |
Learning methods for geometry and appearance reconstruction
Božidar Antić (Ph.D. Student)
As XR technologies are gaining more traction, estimating detailed geometry and appearance of scenes and humans is becoming a crucial task in order to have realistic and interactive virtual experiences. The majority of today's methods focus only on reconstructing geometry and simple textures. However, estimation of u...
| Primary Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Siyu Tang (ETH Zürich) |
| PhD Duration: | 01 December 2021 - 31 October 2025 |
| Exchange Duration: | 01 June 2023 - 30 November 2023 |
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...
| Primary Host: | Otmar Hilliges (ETH Zürich) |
| Exchange Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 March 2019 - 28 February 2023 |
| Exchange Duration: | 01 January 2021 - 31 December 2021 |
Learning to solve Differential Equations with Uncertainty
Emilia Magnani (Ph.D. Student)
Learning differential equations is an emerging research theme in machine learning. Differential equations are interesting because they offer a powerful language for dynamical relationships between variables and a mechanism for reduction for structured models, which is especially relevant in science. The project will...
| Primary Host: | Philipp Hennig (University of Tübingen) |
| Exchange Host: | Lorenzo Rosasco (University of Genoa, Italian Institute of Technology & Massachusetts Institute of Technology) |
| PhD Duration: | 01 December 2020 - 30 November 2023 |
| Exchange Duration: | 01 December 2021 - 28 February 2022 01 December 2022 - 28 February 2023 |
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...
| Primary Host: | Tomas Pajdla (Czech Technical University) |
| Exchange Host: | Konrad Schindler (ETH Zürich) |
| PhD Duration: | 01 February 2022 - 01 February 2026 |
| Exchange Duration: | 01 February 2023 - 01 August 2023 |
Learning with Limited Data
Yingjun Du (Ph.D. Student)
In clinical practices, massive annotations are difficult to acquire in some conditions where specialized biomedical expert knowledge is required. Inspired by the human ability to learn new tasks quickly from a small number of examples, few-shot learning attempts to address the challenge of training artificial intelli...
| Primary Advisor: | Cees Snoek (University of Amsterdam) |
| Industry Advisor: | Xiantong Zhen (University of Amsterdam & Inception Institute of Artificial Intelligence) |
| PhD Duration: | 01 June 2020 - 31 May 2024 |
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...
| Primary Advisor: | Bernt Schiele (Max Planck Institute for Informatics & Saarland University) |
| Industry Advisor: | Anna Khoreva (Bosch Center for AI) |
| PhD Duration: | 01 April 2019 - 30 September 2022 |
Long-Horizon Dexterous Manipulation from Demonstration
Adrian Röfer (Ph.D. Student)
Everyday human environments are highly complex in both structure, and appearance. Nonetheless, we would like to move towards a world in which robots can assist and support humans in these environments. As a part of my PhD, I will move us one step along this path by making robotic manipulation more dexterous and ada...
| Primary Host: | Abhinav Valada (University of Freiburg) |
| Exchange Host: | Sethu Vijayakumar (University of Edinburgh & The Alan Turing Institute) |
| PhD Duration: | 01 June 2021 - 31 May 2025 |
| Exchange Duration: | 01 June 2023 - 30 November 2023 |
Machine learning and AI for secure and trustworthy autonomous systems
Oishi Deb (Ph.D. Student)
The project focuses on trustworthy-autonomous systems which include working on explainable-by-design/interpretable Deep Learning models 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 Syste...
| Primary Host: | Plamen P. Angelov (Lancaster University) |
| Exchange Host: | Aude Billard (EPFL) |
| PhD Duration: | 01 October 2021 - 31 March 2024 |
| Exchange Duration: | 01 June 2022 - 31 August 2022 01 June 2023 - 31 August 2023 |
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...
| Primary Host: | Karsten Borgwardt (ETH Zürich) |
| Exchange Host: | Kristel Van Steen (University of Liège & KU Leuven) |
| PhD Duration: | 01 March 2020 - 31 December 2022 |
| Exchange Duration: | 01 November 2020 - 31 January 2021 |
Machine learning approach for multi-scale genomics problems
Olga Mineeva (Ph.D. Student)
In the age of rapid growth of available biological sequencing data enabled by the recent advances in sequencing technologies, there is an opportunity to answer biological and health-related questions at a more detailed level. At the same time, the amount of data allows the use of sophisticated methods, such that dee...
| Primary Host: | Gunnar Rätsch (ETH Zürich) |
| Exchange Host: | Isabel Valera (Saarland University & Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 November 2018 - 31 October 2022 |
| Exchange Duration: | 01 January 2020 - 30 June 2020 |
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 ...
| Primary Host: | Karsten Borgwardt (ETH Zürich) |
| Exchange Host: | Volker Tresp (LMU Munich & Siemens) |
| PhD Duration: | 01 September 2019 - 31 August 2022 |
| Exchange Duration: | 01 February 2021 - 30 April 2021 |
Machine learning for improving climate models
Fernando Iglesias-Suarez (PostDoc)
Earth system and climate models are fundamental to understanding and projecting climate change. Although they have improved significantly over the last decades, considerable biases compared to observations and uncertainties in their projections still remain. We will take a new approach by harvesting output from high...
| Primary Host: | Veronika Eyring (German Aerospace Center (DLR) & University of Bremen) |
| Exchange Host: | Gustau Camps-Valls (Universitat de València) |
| PostDoc Duration: | 01 December 2019 - Ongoing |
| Exchange Duration: | 01 July 2020 - 31 December 2022 |
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...
| Primary Host: | Fabian Theis (Helmholtz Center Munich) |
| Exchange Host: | Karsten Borgwardt (ETH Zürich) |
| PhD Duration: | 01 August 2021 - 31 July 2024 |
| Exchange Duration: | - Ongoing |
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...
| Primary Host: | Xiaoxiang Zhu (German Space Center (DLR) & Technical University of Munich) |
| Exchange Host: | Devis Tuia (EPFL) |
| PhD Duration: | 01 October 2019 - 30 September 2023 |
| Exchange Duration: | 01 September 2020 - 31 December 2020 |
Machine learning methods for graph-structured data
Leslie O'Bray (Ph.D. Student)
Alongside the rise of machine learning methods has been an increase in graph-structured data, which captures rich and complex relationships in the data. Since many machine learning methods do not work out-of-the box with graph-structured data, specific research and focus is necessary to develop such methods to enabl...
| Primary Host: | Karsten Borgwardt (ETH Zürich) |
| Exchange Host: | Michael Bronstein (Imperial College London) |
| PhD Duration: | 01 October 2019 - 31 October 2023 |
| Exchange Duration: | 15 January 2022 - 14 July 2022 |
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...
| Primary Host: | Jens Eisert (Free University of Berlin) |
| Exchange Host: | Vedran Dunjko (Leiden University) |
| PhD Duration: | 01 October 2021 - 30 September 2024 |
| Exchange Duration: | 01 October 2023 - 01 April 2024 |
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.
| Primary Advisor: | Max Welling (University of Amsterdam) |
| Industry Advisor: | Maja Rudolph (Bosch Center for AI) |
| PhD Duration: | 01 October 2019 - 01 March 2024 |
Methods of feature attribution for interpretability
Jae Myung Kim (Ph.D. Student)
In this project, our goal is to design reliable machine learning methods that can be understood by humans. We propose to tackle this goal in three different ways: (1) Interpreting the decision of black-box AI models to make it transparent, (2) making self-explainable AI models for better reliability, and (3) alignin...
| Primary Host: | Zeynep Akata (University of Tübingen) |
| Exchange Host: | Cordelia Schmid (INRIA) |
| PhD Duration: | 01 August 2021 - 31 July 2024 |
| Exchange Duration: | 01 February 2024 - 31 July 2024 |
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...
| Primary Host: | Otmar Hilliges (ETH Zürich) |
| Exchange Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 July 2021 - 30 June 2025 |
| Exchange Duration: | 01 January 2022 - 01 January 2023 |
Modelling Clothed Humans via Neural Implicit Representations
Shaofei Wang (Ph.D. Student)
This project aims at registration and generation of clothed humans in 3D. The first part of this project concerns registering parametric human body models, e.g. poses and shapes, to sensor inputs such as RGBD images. The second part of this project will tackle the problem of building a controllable neural implicit r...
| Primary Host: | Siyu Tang (ETH Zürich) |
| Exchange Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 September 2020 - 30 June 2024 |
| Exchange Duration: | 01 May 2022 - 30 November 2022 |
Multi-Task Learning for Medical Image Analysis and Data Mining
Jiayi Shen (Ph.D. Student)
Multi-task learning is a fundamental learning paradigm for machine learning, which aims to simultaneously solve multiple related tasks to improve the performance of individual tasks by sharing knowledge. The crux of multi-task learning is to explore task relatedness to improve each individual task, which is non-triv...
| Primary Advisor: | Marcel Worring (University of Amsterdam) |
| Industry Advisor: | Xiantong Zhen (University of Amsterdam & Inception Institute of Artificial Intelligence) |
| PhD Duration: | 01 June 2020 - 01 June 2024 |
Multimodal Learning
Chen Liu (Ph.D. Student)
The human learning experience is multimodal. We utilize information from both language and vision, along with other contextual clues, to understand, reason, and communicate in social settings. In this project, we aim to utilize textual and visual information to solve different NLP tasks, such as classification, gene...
| Primary Host: | Iryna Gurevych (Technical University of Darmstadt) |
| Exchange Host: | Anna Korhonen (University of Cambridge) |
| PhD Duration: | 01 October 2021 - 30 September 2024 |
| Exchange Duration: | 01 January 2024 - 30 June 2024 |
Multimodal video learning
Yunhua Zhang (Ph.D. Student)
Video streams consist of multiple modalities, e.g., RGB frames, optical flow, audio. Their natural correspondence provides rich semantic information to achieve effective multi-modal perception and learning. In this project, our aim is to understand the video content by analyzing multiple modalities and decide which ...
| Primary Advisor: | Cees Snoek (University of Amsterdam) |
| Industry Advisor: | Xiantong Zhen (University of Amsterdam & Inception Institute of Artificial Intelligence) |
| PhD Duration: | 01 October 2019 - 30 September 2023 |
Neural Architecture Search
Binxin Ru (Ph.D. Student)
The success of machine learning algorithms relies heavily on the appropriate choices of model architectures and hyperaparameters. Designing a model often requires strong expertise and selecting these hyperparameters are traditionally done via laborious trial and error. This has created strong demand for ways to auto...
| Primary Host: | Michael A. Osborne (University of Oxford) |
| Exchange Host: | Frank Hutter (University of Freiburg) |
| PhD Duration: | 01 October 2017 - 31 December 2021 |
| Exchange Duration: | 01 July 2021 - 31 October 2021 |
Neural Machine Translation with Latent Context
Gonçalo Correia (Ph.D. Student)
Transformers have become ubiquitous in generative models and, most notably, in NLP, where large and pre-trained all-purpose models are released often and achieve new state-of-the-art results. These architectures are mainly comprised of multiple layers of attention mechanisms, which not only results in powerful repre...
| Primary Host: | André Martins (University of Lisbon) |
| Exchange Host: | Vlad Niculae (University of Amsterdam) |
| PhD Duration: | 01 April 2018 - 30 April 2022 |
| Exchange Duration: | 01 April 2020 - 30 June 2020 01 October 2021 - 31 March 2022 |
Object-centric visual retrieval in the wild
Alaaeldin El-Nouby (Ph.D. Student)
The objective of this thesis is to automatically extract massive amounts of visual and statistical information from large image collections. In particular, the objective which will direct the research is that of the creation of a visual catalog of the objects appearing in an image collection. Such information is of ...
| Primary Advisor: | Ivan Laptev (INRIA) |
| Industry Advisor: | Hervé Jégou (Facebook) |
| PhD Duration: | 03 August 2020 - 03 August 2023 |
Open-Ended Multi-Agent Reinforcement Learning
Mikayel Samvelyan (Ph.D. Student)
Despite the recent success of reinforcement learning (RL), modern RL methods face numerous challenges that prohibit their wide usage in the real world. Reality is dynamic, open-ended, continually changing, and multi-agent by nature. Therefore, RL algorithms need to be robust to variation in their environments and ot...
| Primary Advisor: | John Shawe-Taylor (University College London) |
| Industry Advisor: | Tim Rocktäschel (University College London & Meta AI) |
| PhD Duration: | 28 September 2020 - 27 September 2024 |
Out-of-distribution Generalization
Zehao Xiao (Ph.D. Student)
Out-of-distribution (OoD) generalization is a common task in machine learning. Deep neural networks have exhibited remarkable performance over various computer vision and machine learning tasks. However, they struggle and lack robustness when the test data are in different distributions from the training data. These...
| Primary Advisor: | Cees Snoek (University of Amsterdam) |
| Industry Advisor: | Xiantong Zhen (University of Amsterdam & Inception Institute of Artificial Intelligence) |
| PhD Duration: | 01 June 2020 - 31 May 2024 |
Persistent Impacts in Vegetation and Extreme Events
Tristan Williams (Ph.D. Student)
Persistence is an important characteristic of many complex systems in nature and of the Earth system in particular. The concept is rather elusive but related to how long the system remains at a certain state before changing to a different one. Characterising persistence in the terrestrial biosphere is very relevant ...
| Primary Host: | Gustau Camps-Valls (Universitat de València) |
| Exchange Host: | Miguel D. Mahecha (Leipzig University & Max Planck Institute for Biogeochemistry) |
| PhD Duration: | 01 March 2023 - 01 September 2023 |
| Exchange Duration: | - Ongoing |
Primal-Dual Methods for Reinforcement Learning
Antoine Moulin (Ph.D. Student)
Empirical research in reinforcement learning has achieved impressive results over the past few years. However, many questions remain open regarding the theoretical guarantees of the algorithms used in practice. The PhD project aims to gain a deeper understanding of the challenges posed by large-scale reinforcement l...
| Primary Host: | Gergely Neu (Universitat Pompeu Fabra) |
| Exchange Host: | Arthur Gretton (University College London) |
| PhD Duration: | 01 December 2021 - 01 July 2025 |
| Exchange Duration: | 01 October 2022 - 31 January 2023 01 July 2024 - 01 October 2024 |
Privacy-preserving data sharing via probabilistic models
Joonas Jälkö (Ph.D. Student)
Widespread sharing of data would facilitate rapid progress in data science. However, due to privacy constraints, sensitive data cannot be made public. My research aims to learn a generative model from the sensitive data under strict privacy guarantees from differential privacy. The generative model is then used to d...
| Primary Host: | Samuel Kaski (Aalto University, Finnish Centre for AI & University of Manchester) |
| Exchange Host: | Mihaela van der Schaar (University of Cambridge, The Alan Turing Institute & University of California) |
| PhD Duration: | 16 November 2018 - 16 November 2022 |
| Exchange Duration: | - Ongoing |
Probabilistic Approaches for Maximally Autonomous AI Assistants
Nazaal Ibrahim (Ph.D. Student)
Much of modern AI focuses on explicit problem formulations, with full autonomy preferred if possible. In this project, we relax this last constraint and aim to develop methods for AI assistants where we may instead prefer maximal autonomy. Such problems arise naturally in critical decision making systems and various...
| Primary Host: | Samuel Kaski (Aalto University, Finnish Centre for AI & University of Manchester) |
| Exchange Host: | Stefano V. Albrecht (University of Edinburgh & The Alan Turing Institute) |
| PhD Duration: | 01 October 2021 - 30 September 2025 |
| Exchange Duration: | - Ongoing |
Probabilistic Reasoning with Neural Networks Beyond Weight Space
Javier Antorán (Ph.D. Student)
Neural networks are a flexible class of models that have soared in popularity due to their scalability to large amounts of data and computation. The fact that these models are able to represent a very broad range of functions makes performing Bayesian inference in them challenging. Most existing approaches focus on ...
| Primary Host: | José Miguel Hernández-Lobato (University of Cambridge) |
| Exchange Host: | Max Welling (University of Amsterdam) |
| PhD Duration: | 01 October 2019 - 31 May 2023 |
| Exchange Duration: | 01 January 2022 - 30 June 2022 |
Provable Robustness of Intelligent Systems for Realistic Threats and Tasks
Tobias Lorenz (Ph.D. Student)
The trustworthiness of intelligent systems is prudent for their deployment in many real-world environments. A major aspect of such trustworthy systems is to ensure their reliability under adverse conditions, even in the presence of malicious adversaries. Unfortunately, there is an abundance of techniques to evade an...
| Primary Host: | Mario Fritz (CISPA Helmholtz Center for Information Security, Saarland University) |
| Exchange Host: | Marta Kwiatkowska (University of Oxford) |
| PhD Duration: | 01 April 2021 - 31 July 2025 |
| Exchange Duration: | 01 May 2023 - 31 October 2023 |
Relaxed gradient estimators for structured probabilistic models
Max Paulus (Ph.D. Student)
Gradient computation is the methodological backbone of deep learning, but computing gradients can be challenging, in particular for some structured probabilistic models. Such models are of interest for a number of reasons, including improving interpretability, incorporating problem-specific constraints or improving ...
| Primary Host: | Andreas Krause (ETH Zürich) |
| Exchange Host: | Chris J. Maddison (University of Toronto & DeepMind) |
| PhD Duration: | 01 April 2018 - Ongoing |
| Exchange Duration: | 01 June 2019 - 31 December 2019 |
Representation Learning over Multi-Relational Graphs
Yihong Chen (Ph.D. Student)
One of the main characteristics of human intelligence is the ability to reason over relationships among various entities. Multi-relational graphs, specifically knowledge graphs, are an excellent way to capture such relational knowledge. Good representation learning over multi-relational graphs fosters downstream app...
| Primary Advisor: | Pontus Stenetorp (University College London) |
| Industry Advisor: | Sebastian Riedel (University College London & Facebook) |
| PhD Duration: | 23 September 2019 - 23 September 2023 |
Representation Learning with Deep Generative Models
Andrea Dittadi (Ph.D. Student)
Learning useful representations from data with little or no supervision is a key challenge in artificial intelligence. Firstly, while labeled data is typically expensive, vast amounts of unlabeled data are available. Secondly, although the usefulness of a representation depends on the downstream task, it should be p...
| Primary Host: | Ole Winther (University of Copenhagen & Technical University of Denmark) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 15 March 2018 - 15 April 2022 |
| Exchange Duration: | 23 February 2020 - 31 August 2020 |
Robust and Reproducible Neural Architecture Search
Arber Zela (Ph.D. Student)
Neural Architecture Search (NAS) is the next logical step towards the automation of deep learning systems, due to its potential to achieve state-of-the-art performance on various tasks and remove the need of manually designing neural network architectures. The first black-box NAS methods required a vast amount of co...
| Primary Host: | Frank Hutter (University of Freiburg) |
| Exchange Host: | Yee Whye Teh (University of Oxford & DeepMind) |
| PhD Duration: | 01 March 2019 - Ongoing |
| Exchange Duration: | 01 July 2021 - 31 August 2021 |
Sample Efficient Reinforcement learning via Language Abstractions
Fabian Paischer (Ph.D. Student)
Deep Reinforcement learning has gained plenty of attention recently through mastering highly complex games, such as StarCraft II. Many difficult problems arise in such games, for example dealing with partial observability, or continuous state and action spaces. To cope with such problems, current algorithms require ...
| Primary Host: | Sepp Hochreiter (Johannes Kepler University Linz) |
| Exchange Host: | Marc Deisenroth (University College London) |
| PhD Duration: | 01 October 2021 - Ongoing |
| Exchange Duration: | 01 February 2023 - 01 August 2023 |
Semantic Labeling of Multisensory 3D Point Clouds
Yuxing Xie (Ph.D. Student)
Benefiting from the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, point clouds are becoming more significant and accessible than before. In addition to widely-used LiDAR point clouds, satellite stereo imagery- and InSAR- based 3D data also cannot be...
| Primary Host: | Xiaoxiang Zhu (German Space Center (DLR) & Technical University of Munich) |
| Exchange Host: | Konrad Schindler (ETH Zürich) |
| PhD Duration: | 01 August 2018 - Ongoing |
| Exchange Duration: | 01 September 2020 - 31 December 2020 |
Statistical Inference in Deep Science-Aware Models
Kai-Hendrik Cohrs (Ph.D. Student)
Science-aware and science-guided machine learning attempts to combine knowledge of first principles and machine learning. One way of doing so is using explicit equations from theoretical knowledge and estimate parameters or latent states with machine learning approaches. This promises scientifically interpretable re...
| Primary Host: | Gustau Camps-Valls (Universitat de València) |
| Exchange Host: | Markus Reichstein (Max Planck Institute for Biogeochemistry) |
| PhD Duration: | 01 October 2021 - 30 September 2024 |
| Exchange Duration: | 01 August 2022 - 31 October 2022 01 August 2023 - 31 October 2023 |
Statistical Modeling of Dynamical Systems
Philippe Wenk (Ph.D. Student)
This dissertation project aims at providing a robust, scalable inference technique for parametric models of time series. In particular, it focuses on Gaussian process based collocation methods, investigating the weaknesses of existing ideas and developing new algorithms for parameter inference in systems of ODEs and...
| Primary Host: | Andreas Krause (ETH Zürich) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 May 2018 - 01 May 2021 |
| Exchange Duration: | 01 May 2020 - 01 August 2020 |
Temporal Causality in Machine Learning
Phillip Lippe (Ph.D. Student)
The field of Causality is concerned with finding and understanding the effect that a change of a variable has on other variables in an environment. Meanwhile, current machine learning approaches typically rely on correlations in data but lack the clear separation of cause and effect. This can lead to problems when t...
| Primary Advisor: | Efstratios Gavves (University of Amsterdam) |
| Industry Advisor: | Taco Cohen (Qualcomm AI Research) |
| PhD Duration: | 15 September 2020 - 14 September 2024 |
The intersection of causality and NLP
Zhijing Jin (Ph.D. Student)
The PhD project aims to bridge the connection between two areas that have long been developed separately, causal inference and natural language processing (NLP). Specifically, we aim at the following goals: (1) methodological improvements of NLP models using causal inference theories, and (2) applying causality+NLP ...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Ryan Cotterell (ETH Zürich & University of Cambridge) |
| PhD Duration: | 01 January 2021 - 31 December 2023 |
| Exchange Duration: | 01 January 2023 - 30 June 2023 |
Towards Bayesian Neural Model Selection
Alexander Immer (Ph.D. Student)
Model selection and comparison, the task of choosing the optimal model for a given data set, is a central problem in machine learning. Model selection is particularly challenging for deep neural networks because of their ability to represent arbitrary functions and their enormous size and overparameterization. For t...
| Primary Host: | Gunnar Rätsch (ETH Zürich) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 July 2020 - 31 July 2024 |
| Exchange Duration: | 01 February 2022 - 31 January 2023 |
Towards Semantic Speech Processing
Lasse Borgholt (Ph.D. Student)
Human spoken language understanding relies heavily on contextual information. If we consider a single word, the context might simply be the words surrounding it. These words provide important clues for the listener to accurately recognize and understand the word of interest. This word may be hard to recognize becaus...
| Primary Advisor: | Christian Igel (University of Copenhagen) |
| Industry Advisor: | Lars Maaløe (Corti.ai & Technical University of Denmark) |
| PhD Duration: | 01 February 2019 - 01 February 2022 |
Trustworthy Machine Learning for safety-critical applications
Maximilian Müller (Ph.D. Student)
Deploying Machine Learning systems in safety-critical real-world scenarios such as the medical domain poses particular challenges. Often, classes are semantically very similar and the data available for training is noisy and suffers from high class-imbalance. Further, modern Machine Learning systems, despite being t...
| Primary Host: | Matthias Hein (University of Tübingen) |
| Exchange Host: | Gergely Neu (Universitat Pompeu Fabra) |
| PhD Duration: | 18 October 2021 - Ongoing |
| Exchange Duration: | 01 September 2022 - 01 March 2023 |
Trustworthy Self-Attentive Models for Visual-Semantic Understanding
Roberto Amoroso (Ph.D. Student)
Deep learning has quickly become the state-of-the-art approach for extracting knowledge from visual data and it is rapidly solving some of the most complex problems in Computer Vision, such as image classification, object detection, and visual-semantic understanding with supervised learning. As Deep Learning gets be...
| Primary Host: | Rita Cucchiara (Università di Modena e Reggio Emilia) |
| Exchange Host: | Stefan Roth (Technical University of Darmstadt) |
| PhD Duration: | 01 November 2021 - 31 October 2024 |
| Exchange Duration: | - Ongoing |
Uncertainty estimation for machine learning system self-assessment on medical conversations
Jakob Havtorn (Ph.D. Student)
This project will develop extensions of probabilistic generative modelling to efficiently handle high-dimensional sequence and time-series data, such as audio, and show that robust semi-supervised learning, reliable out-of-distribution detection and uncertainty estimation can be achieved. In real-world applications,...
| Primary Advisor: | Jes Frellsen (Technical University of Denmark) |
| Industry Advisor: | Lars Maaløe (Corti.ai & Technical University of Denmark) |
| PhD Duration: | 01 September 2020 - 31 August 2023 |
Uncertainty estimation in deep neural networks
Raphael Sayer (Ph.D. Student)
In many classification tasks in machine learning not just the predicted label but also the estimated probability of that label is of interest. While regularly achieving high prediction accuracies, deep neural network classifiers usually ouput label probabilities that do not match the true underlying probability dist...
| Primary Host: | Matthew Blaschko (KU Leuven) |
| Exchange Host: | Philipp Hennig (University of Tübingen) |
| PhD Duration: | 01 April 2021 - 01 April 2025 |
| Exchange Duration: | 01 April 2023 - 30 September 2023 |
Uncertainty Quantification in Deep Learning
Jihao Andreas Lin (Ph.D. Student)
In recent years, deep learning has achieved remarkable success at advancing complex tasks, such as computer vision and natural language processing. While deep learning models and algorithms are already being used in some industry and consumer applications, a lack of interpretability and trustworthiness is obst...
| Primary Host: | José Miguel Hernández-Lobato (University of Cambridge) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2022 - 30 September 2026 |
| Exchange Duration: | 01 October 2025 - 30 September 2026 |
Unsupervised cross domain detection and retrieval from scarce data for monitoring of images in social media feeds
Eros Fani (Ph.D. Student)
Social media feeds us every day with an unprecedented amount of visual data. Conservative estimates indicate that roughly 10^1‐10^2M unique images are shared everyday on Twitter, Facebook and Instagram. Images are uploaded by various actors, from corporations to political parties, institutions, entrepreneurs and pri...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Bernhard Nessler (Johannes Kepler University Linz) |
| PhD Duration: | 01 November 2021 - 31 October 2024 |
| Exchange Duration: | 01 February 2024 - 01 August 2024 |
Video-Text Learning
Simon Ging (Ph.D. Student)
Language is a great code for semantic knowledge, of which humans make plenty of use. In this thesis, we want to find ways of leveraging the large semantic base of world knowledge coded as language for interpreting visual scenes. This requires visual grounding to align visual content with language. A currently quite ...
| Primary Host: | Thomas Brox (University of Freiburg) |
| Exchange Host: | Konrad Schindler (ETH Zürich) |
| PhD Duration: | 01 May 2021 - 30 April 2024 |
| Exchange Duration: | - Ongoing |
Weakly-Supervised Multi-Modal Learning for Scene Understanding
Antonín Vobecký (Ph.D. Student)
The objective of the research is to improve the accuracy of machine learning models under the conditions of low amounts of annotated training/testing data as well as the lack of correctly defined data distributions in the context of autonomous driving applications. The key open problem in these low-data regimes is l...
| Primary Advisor: | Josef Sivic (Czech Technical University, École Normale Supérieure & INRIA) |
| Industry Advisor: | Patrick Pérez (Valeo.ai) |
| PhD Duration: | 01 October 2019 - 01 September 2023 |
Bayesian Continual Learning
In many real world scenarios, an agent has to face a dynamic environment, where data is not drawn i.i.d from a stationary distribution, but rather changes over time. Continual learning represents a general framework for such scenarios that, in contrast to the standard case where a fixed training and test set is provi...
| Primary Host: | Cédric Archambeau (Amazon) |
| Exchange Host: | Richard E. Turner (University of Cambridge) |
| PostDoc Duration: | 01 July 2019 - 30 June 2021 |
| Current Affiliation: | Amazon Research Berlin |
Fairness and Discrimination Mitigation in Rankings
My research interests center around artificial intelligence and its social impact, algorithmic discrimination, fairness and algorithmic exploitation. In my PhD thesis, I develop methods to detect and mitigate discriminatory patterns that make their way into ranking models. Such biased models usually lead to disparit...
| Primary Host: | Krishna P. Gummadi (Max Planck Institute for Software Systems) |
| Exchange Host: | Carlos Castillo (Universitat Pompeu Fabra) |
| PhD Duration: | 01 April 2016 - 30 April 2021 |
| Current Affiliation: | Zalando Research |
Flexible Densities for Deep Generative Models
Probability distributions play a central role in machine learning. For probabilistic modeling, they are used as likelihoods and prior distributions, whereas in variational inference, they are employed as approximate posterior distributions. The probability distributions typically used in practice tend to be simple...
| Primary Host: | Ole Winther (University of Copenhagen & Technical University of Denmark) |
| Exchange Host: | Max Welling (University of Amsterdam) |
| PhD Duration: | 01 January 2019 - 31 December 2021 |
| Current Affiliation: | Norwegian Computing Center |
Generalization out of distribution
While current techniques in machine learning have been showing tremendous success at generalization in the i.i.d. setting when large quantities of data and compute are available, performance consistently drops as soon as we try to extend our models to data out of distribution. Tasks such as transfer learning, meta-l...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Thomas Hofmann (ETH Zürich) |
| PhD Duration: | 01 March 2017 - 01 October 2021 |
| Current Affiliation: | OpenAI |
Geometric deep learning and partial differential equations
Partial differential equations (PDEs) are used in physics, engineering and many other scientific disciplines. While their numerical solutions have been a longstanding challenge, deep learning methods offer an appealing meshfree approach. On the other hand, PDEs are a language in which we can express inductive biases...
| Primary Host: | Sepp Hochreiter (Johannes Kepler University Linz) |
| Exchange Host: | Max Welling (University of Amsterdam) |
| PostDoc Duration: | 01 January 2021 - 31 January 2022 |
| Current Affiliation: | Microsoft Research |
Learning Deep Models with Primitive-based Representations
My research so far seeks to give an answer to a very simple question, how can we teach machines to learn to see in 3D? Or in other words, what is the best representation, that would allow us to capture the world such that a machine would be able to robustly perceive it? Humans develop a common-sense understanding of...
| Primary Host: | Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Luc Van Gool (ETH Zürich & KU Leuven) |
| PhD Duration: | 01 April 2017 - 01 November 2021 |
| Current Affiliation: | Stanford University |
Learning Robotic Manipulation from Instructional Videos
The objective of the project is to enable robots to learn new manipulation skills from instructional videos available online. We will study how instructional videos could be used to overcome the sparse reward problem in reinforcement learning. The sparse reward complicates reinforcement learning by assigning the rew...
| Primary Host: | Josef Sivic (Czech Technical University, École Normale Supérieure & INRIA) |
| Exchange Host: | Ivan Laptev (INRIA) |
| PostDoc Duration: | 01 April 2019 - 31 March 2020 |
| Current Affiliation: | Czech Technical University in Prague |
Machine Learning for Molecules
Machine Learning has enormous potential in augmenting scientists' capabilities in discovering novel drugs or new materials. To achieve this we need to develop ML models that can accurately predict properties of molecules and their interactions, as well as techniques that enable intelligent searching of discrete and ...
| Primary Host: | José Miguel Hernández-Lobato (University of Cambridge) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2016 - 23 July 2021 |
| Current Affiliation: | Massachusetts Institute of Technology |
Priors and Inference for Deep Probabilistic Models
While deep learning techniques have led to impressive advances in supervised and representation learning, this was mostly in domains where large homogeneous sets of structured data are available. In contrast, probabilistic models are more data-efficient and often provide better interpretability as well as uncertaint...
| Primary Host: | Gunnar Rätsch (ETH Zürich) |
| Exchange Host: | Richard E. Turner (University of Cambridge) |
| PhD Duration: | 01 November 2017 - 30 November 2021 |
| Current Affiliation: | University of Cambridge |
Safety and robustness in reinforcement learning
Reinforcement learning has achieved impressive results in recent years through learning by trial and error. However, many real-world applications are subject to safety constraints that should not be violated at any time. In these cases, autonomous agents that can reason about safety while exploring and learning abou...
| Primary Host: | Andreas Krause (ETH Zürich) |
| Exchange Host: | Sebastian Trimpe (RWTH Aachen University) |
| PhD Duration: | 26 September 2016 - 31 March 2021 |
| Current Affiliation: | ETH Zürich |
Socially Beneficial Machine Learning
As machine learning touches upon all areas of our daily lives, it is increasingly deployed to make or support consequential decisions about individuals. Such applications raise concerns about privacy violations, the fairness of algorithms, as well as the long-term impact automated decisions might have on individuals...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Carl Edward Rasmussen (University of Cambridge) |
| PhD Duration: | 01 October 2016 - 14 September 2020 |
| Current Affiliation: | Helmholtz AI |
Stochastic Convex Optimization for Over-Parametrized models
Over-parametrized models are frequently occurring phenomena in machine learning which comes with nice properties. In this work, we investigate methods to optimize such models. Our goal is to show faster convergence rate for traditional 1st order methods on such problems without extra assumptions and with similar com...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Francis Bach (INRIA & École Normale Supérieure) |
| PhD Duration: | 01 August 2015 - 30 November 2020 |
| Current Affiliation: | UIUC & INRIA |
Structured probabilistic inference via efficient constrained optimization
In my research, I focus on enforcing desirable properties to the solution of learning algorithms, such as incorporating human beliefs, natural constraints, and causal structures. This translates to faster, more accurate, and more flexible models, which directly relates to real-world impact. I tackle this challenge...
| Primary Host: | Gunnar Rätsch (ETH Zürich) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2016 - 31 December 2020 |
| Current Affiliation: | Amazon AWS |
Theory of latent feature learning
Low dimensional, abstract or otherwise 'simple' structure occurs widely across machine learning. This project advances theoretical understanding in a variety of areas. These are: causality, in which a theory of micro-macro abstractions is developed; independent component analysis, in which new identifiability result...
| Primary Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| Exchange Host: | Carl Edward Rasmussen (University of Cambridge) |
| PhD Duration: | 01 October 2015 - 30 June 2020 |
| Current Affiliation: | Apple |
Trustworthy Machine Learning
Key to the recent success of machine learning algorithms is the availability of large data sets for training models. The scale and variability of the needed data, however, often enforces its collection from various, potentially unreliable sources. Previous work has shown that machine learning models are vulnerable t...
| Primary Host: | Christoph H. Lampert (IST Austria) |
| Exchange Host: | Nicolò Cesa-Bianchi (Università degli Studi di Milano) |
| PhD Duration: | 15 September 2017 - 15 March 2022 |
| Current Affiliation: | ETH Zürich |
Uncertainty Quantification in Dynamical Systems
Many real-world systems are not static, they evolve through time. Modelling them as dynamical systems enables us to correctly account for non-stationarity and is a natural choice for sequential datasets. Especially in the low data regime, correctly quantifying predictive uncertainty is crucial to ensure we do not ta...
| Primary Host: | Carl Edward Rasmussen (University of Cambridge) |
| Exchange Host: | Bernhard Schölkopf (Max Planck Institute for Intelligent Systems) |
| PhD Duration: | 01 October 2016 - 25 February 2022 |
| Current Affiliation: | Even |
Zero shot adaptation and learning
Domain Adaptation is a transfer learning scenario where the goal is to build a model addressing a task, e.g. classification, in a target domain with no or few images are labeled. Given a large amount of labeled data in a domain, i.e. the source, with a different input distribution from the target, e.g. synthetic to ...
| Primary Host: | Barbara Caputo (Politecnico di Torino & Italian Institute of Technology) |
| Exchange Host: | Zeynep Akata (University of Tübingen) |
| PhD Duration: | 01 November 2016 - 31 October 2020 |
| Current Affiliation: | University of Tübingen |
