Thesis offers

A more detailed description of the project can be found in

https://www.cs.upc.edu/~eromero/Downloads/Retina-TFM-Project-01.pdf

The project is proposed in collaboration with Javier Zarranz Ventura
(Institut Clínic d'Oftalmologia, ICOF, Hospital Clínic de Barcelona, and
Institut d'Investigacions Biomèdiques August Pi I Sunyer, IDIBAPS),
which would provide a large annotated database to develop the project. For further information, please contact Alfredo Vellido (avellido@cs.
upc.edu) or Enrique Romero (eromero@cs.upc.edu).

Functional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technique that measures changes in oxygenated (HbO2) and deoxygenated hemoglobin (HbR) in the cerebral cortex. Due to its portability and low cost, fNIRS has been used in Brain-Computer Interface (BCI) applications, characterizing hemodynamic responses to varying stimuli, and investigating auditory and visual-spatial attention during Complex Scene Analysis (CSA). In this project, we want to design and implement an fNIRS study with a goal of studying the impact of neural and BCI outcomes to improving the training of LAI models' attention mechanism (e.g., Transformer attention) during reading comprehension tasks (e.g., the participants will be judging the quality of generated text). We want to demonstrate experimentally that augmenting a model with fNIRS data carries neural activity features complementing the information captured by the model and demonstrate that it improves the models' performance. To this end, we will have to collect data from participants and test how different Transformer models benefit from different types of fNIRS attention masks.

The candidate will:

• Carry out controlled studies and collect data from a number of participants.
• Try different approaches to incorporating fNIRS signal in the training process of DL/LLM models and compare against baselines/experiments (these should be replicated).
• Carry out ablation studies, personalisation techniques, error analyses, etc.
• Contribute to authoring a scientific article

 State-of-the-art models such as LLMs are too large to fit in a single compute node (GPU, NPU, CPU), both for training and inference on a device (e.g., phone, laptop, tablet) or in larger-scale data centers. There is a need to develop optimization techniques to split and place these models onto a distributed set of compute nodes so that the overall system performance is maximized. The research will be focused on optimizing the placement of AI models onto distributed systems considering training time, energy consumption, and computational resources. 

In this thesis, the student will model and simulate distributed AI workloads using both mathematical frameworks and simulators. This encompasses the modeling of network, compute, and memory components within a distributed architecture. Developing new modules to enhance the modeling process. Evaluating and optimizing various parallelization techniques to improve overall system performance.

The Universitat Politècnica de Catalunya · BarcelonaTech offers Master thesis fellowships in the field of LLM training. The research will be supported by Qualcomm and will be carried out in an environment with a strong interaction with leading experts in the field, with opportunities for doing internships in the company.

More information here: https://www.cs.upc.edu/~jordicf/priv/eda/llm_qc.html

This project offers the candidate a unique opportunity to apply artificial intelligence techniques to real-world challenges in lung cancer research and treatment. As part of this thesis, the candidate will work with datasets, including patient records, genetic data, molecular alterations, treatment outcomes, and exposome data. These datasets will serve as the foundation for developing AI models that address critical challenges in lung cancer treatment, such as predicting patient outcomes and identifying optimal treatment strategies.

The candidate will focus on the following core tasks:

Data Exploration and Preprocessing: The candidate will gain experience in handling complex medical datasets by cleaning, preparing, and structuring the data to ensure it is suitable for advanced AI analysis.

Building AI Models: Using machine learning and deep learning techniques, the candidate will develop models aimed at predicting lung cancer progression, evaluating treatment efficacy, and understanding the impact of various environmental and genetic factors.

Interpretability and Explainability: A significant emphasis will be placed on making AI models interpretable and transparent. The candidate will explore techniques to ensure that the models produced are not just accurate but also explainable, providing healthcare professionals with clear insights into the model's predictions and decisions.

Exploring Interaction Networks: The candidate will analyze interaction networks, studying relationships between patient genetics, environmental factors, and treatment responses to identify key drivers of lung cancer outcomes.

Throughout the project, the candidate will not only gain hands-on experience with cutting-edge AI tools and methodologies but also develop a deeper understanding of AI's role in healthcare. This project provides an impactful opportunity to contribute to a field where AI innovation can directly improve patient outcomes.

The Ride-Sharing Problem (RSP) seeks to efficiently match travelers with similar itineraries and schedules on short notice, yielding substantial social and environmental benefits by reducing the number of cars used for personal travel and optimizing the use of available seat capacity in urban areas.

The static version of RSP is inadequate for real-world applications, as it does not account for the inevitable delays caused by traffic, cancellations, or new services. Therefore, a dynamic version is necessary to accommodate these circumstances.

This TFM proposes the development of a Hybrid Metaheuristic to address the Dynamic RSP, combining Metaheuristic optimization with Agent-based simulation. This optimization method must include the following features:

• Adaptation to traffic conditions.
• Integration of new services en route.
• Management of route cancellations.

Automatic gaze tracking methods have been used in the recent years for various purposes, including measuring ad attention or enabling for gesture-less user-device interactions. Most of these methods have been tested in the desktop setting, while the few reported attempts that addressed the mobile setting report low accuracy and require continuous calibration. Additionally, the aforementioned methods rely on expensive sensors, such as infrared eye trackers, that limit their scaling capacity. Other methods employ touch-based interactions (e.g., tracking zoom/pinch gestures and scroll activity) to produce an estimation of the user gaze which, at best, are weakly correlated with visual attention. However, 42% of the time spent on websites is by mobile users, while similar trends are reported for the percentage of page views per visit, which creates an opportunity for a novel attention measurement technology to take root; one which can offer accurate, reliable, and scalable measurements.

In the proposed project, we are interested in the mobile setting, and propose the use of depth information, on top of the usual RGB (Red, Green, Blue) pixel data acquired by mobile device cameras, to track and quantify visual attention. Depth information can either be estimated with post computer visual processing or acquired directly with high precision, using advanced LiDAR sensors that newer smartphone models are currently equipped with. Furthermore, we propose the use of "lightweight" Deep Learning (DL) techniques to achieve an accurate and robust gaze point estimation without the need of extensive calibration. Unlike prior art, we will consider the use of historical information to inform future predictions and will examine how such models can be tailored to each user by injecting personalized data. In addition, we propose a more lightweight Neural Network (NN) architecture, suitable for the processing power of mobile devices, that also leverages the use of video or photo frames with depth sensory data.

The candidate will:

• Develop an app for iPhone (in Swift) for collecting gaze information and image data (using the device's frontal camera and LiDAR sensors), while completing a simple task of tracking a red dot in a matrix.
• Incorporate in the app the functionality offered by SensingKit,  an open-source mobile sensing framework compatible with iOS specialised in capturing motion, orientation, location and proximity (using iBeacon¿ or Eddystone¿) data and transmitting them on a server over any Internet connection. [https://github.com/SensingKit/SensingKit-iOS]
• Carry out a crowdsourcing study and collect data from a number of participants.
• Train lightweight DL models to predict accurately gaze point estimation, using the collected data, and compare against prior baselines/experiments (these should be replicated).
• Carry out ablation studies, personalisation techniques, error analyses, etc.
• Contribute to authoring a scientific article

Eye movement features are considered to be direct signals reflecting human attention distribution with a low cost to obtain, inspiring researchers to augment language models with eye-tracking (ET) data. In this project, we want to investigate how to operationalise eye tracking (ET) features, such as first fixation duration (FFD) and total reading time (TRT), as the cognitive signals to augment LAI models' attention mechanism (e.g., Transformer attention) during training. We want to demonstrate experimentally that augmenting a model with ET data carries linguistic features complementing the information captured by the model and demonstrate that it improves the models' performance. To this end, we will have to collect data from participants and test how different Transformer models benefit from different types of ET attention masks.

The candidate will:

• Carry out controlled studies and collect data from a number of participants.
• Try different approaches to incorporating gaze features in the training process of DL/LLM models and compare against baselines/experiments (these should be replicated).
• Carry out ablation studies, personalisation techniques, error analyses, etc.
• Contribute to authoring a scientific article

Recent advancements in nanotechnology have enabled the development of means for sensing and wireless communications with unprecedented miniaturization and capabilities, to the point that they can be introduced into the gastrointestinal tract inside a pill or into the bloodstream in the form of passively flowing nanomachines. 

This opens the door to the idea of intra-body communication networks, this is, a swarm of nanosensors inside the human body that use communications to coordinate their actions to sense and localize specific events (lack of oxygen, biomarkers, etc). This can lead to the development of applications such as continuous monitoring of diabetes, detection and localization of cancer micro-tumors, or early detection of blood clots. These possibilities are currently investigated by our team at the N3Cat (www.n3cat.upc.edu).

In this context, we are looking for excellent and self-motivated individuals who are eager to work on developing AI schemes (based on graph neural networks or multi-agent RL) for the detection and localization of events inside of the human body. Data will be gathered with an in-house simulator that integrates mobility models (BloodVoyagerS) and communication models (TeraSim).

Seeing that not all neural networks fit to all problems, and that relational data is present in a wide variety of aspects of our daily life, the main focus of this thesis in N3Cat (www.n3cat.upc.edu) and BNN-UPC (www.bnn.upc.edu) is to explore the possibilities of the Graph Neural Networks (GNNs), whose aim is to learn and model graph-structured relational data. We are looking for students willing to study the uses, architectures, and algorithms of GNNs. To this end, the candidate will work on ONE of the following areas:

• Uses: Applying GNNs in emerging application areas, including but not limited to (1) electroencephalogram (EEG) analysis for Alzheimer's disease detection, epilepsy classification, motor imagery; (2) acceleration of the compilation of quantum computing algorithms
• Architectures: Investigating ways to accelerate the processing of GNNs in multiple computing platforms (CPU, GPU, accelerators).
• Algorithms: Developing meta-learning data-driven models to estimate the accuracy of a GNN for a given graph, without training, through synthetic graph generation and correlation analysis.

The future of communication is taking us beyond traditional terrestrial networks. In the next decade, 6G networks will connect more than just smartphones-they will support flying cars and underwater robots using such high-tech enablers as lasers, satellites, drones, and high-altitude platforms (HAPs, flying at 20-40 km). To make this vision a reality, we need to tackle challenges like ensuring seamless connectivity for high-speed aerial vehicles, enabling underwater data transmission, and predicting large-scale network performance in urban environments. By working on these problems, you will be at the forefront of working on groundbreaking challenges in the rapidly evolving field of 6G and Non-Terrestrial Networks.  

The student will work on one of the following research objectives (or on a sensible combination of them):

- Performance modeling and optimization of communication links with satellites (such as starlink) and high-altitude platforms

- Development of advanced AI-driven beamsteering solutions to improve data transmission in underwater laser communication

- Design of an underwater-to-satellite (or HAP) communication system

- 6G-enabled 3D weather sensing and climate monitoring

- Usage of open big real-world data (e.g., OpenStreetMaps) to predict network coverage and performance in large urban areas, helping to optimize infrastructure deployment

- Design of 6G handover strategies for reliable connections with highly mobile (up to 300 kmh) flying cars/taxis

Quantum computers promise exponential improvements over conventional ones due to the extraordinary properties of qubits. However, a quantum computer faces many challenges relative to the movement of qubits which is completely different from the movement of classical data. This thesis delves into these challenges and proposes solutions to create scalable quantum computing systems and the algorithms that run within them, following the current European projects at N3Cat (www.n3cat.upc.edu) on scalable quantum computing.

The interested candidate will work in a group of several PhD students and in collaboration with Universitat Politècnica de València, working in ONE of the following areas:

• Study the use of AI to model quantum computers or to assist in the development of architectural methods (qubit mapping, qubit partitioning, qubit routing).
• Study the potential scaling and adaptation of the existing quantum computing architectures to specific quantum machine learning algorithms (QAOA, VQE, others).

The aim is to enhance the capabilities of small UAVs by integrating RGB AI decks and exploring novel GenAI approaches for 3D object reconstruction. The project will involve developing and refining the UAV setup, conducting experiments with different GenAI techniques, and evaluating the performance across various use cases.

· Extend UAV systems with RGB AI decks for enhanced image capture and processing.

· Explore different Generative AI approaches to enhance the quality of 3D reconstructions.

· Evaluate the performance of the system across different object types and scenarios.

· Conduct experiments to compare reconstruction quality, processing time, and adaptability of dif-

ferent GenAI techniques.

Protein design has flourished in recent years thanks to the application of deep learning algorithms, culminating in the award of the Nobel Prize in Chemistry in 2024. The possibility of designing proteins with tailor-made functions ("à la carte") has enticing applications in drug design, diagnostics, and environmental science, such as the design of catalyists or biosensors. Unfortunately, linking structure to function is not trivial and often requires understanding protein flexibility and dynamics.

The state-of-the-art tool used to generate protein sequences for a given structure is ProteinMPNN, but it has been trained on crystallographic static structures and therefore poorly accounts for protein dynamics. Until 2025, it was impossible to efficiently generate large numbers of protein conformations to account for flexibility, but recent generative methods have proven both precise and effective at low computational cost. This opens the possibility of fine-tuning ProteinMPNN with ensembles of conformations associated with each sequence, thereby encoding protein dynamics into the designed sequences.

The goal of the present TFM is to:

1. Generate ensembles of protein structures with a generative model (such as BioEmu).

2. Fine-tune ProteinMPNN using data augmentation, associating each protein sequence not with a single structure (as done so far) but with an ensemble of structures.

By linking protein dynamics to sequence, this work will represent a significant step forward in the design of de novo functional proteins.

Both BioEmu and ProteinMPNN are open-source and available on GitHub, along with training instructions. The resulting code will also be deposited in GitHub for use by the scientific community.