If you are interested, we can discuss a topic of interest to be done in collaboration with AIKO Space.
Motivation
Compact and reproducible terrain representations can enable new research advancements. While recent studies have shown that terrain can be represented with continuous and differentiable neural models, these approaches have not yet been fully explored for onboard, memory-constrained orthorectification. The objective of this thesis is to design a lightweight deep learning model that approximates a local DEM from spatial coordinates, with the goal of replacing or compressing traditional raster-based elevation data while maintaining sufficient geometric accuracy for fast deployment on edge or satellite systems. Since current solutions are still centered on discrete terrain grids or larger processing pipelines, there is room to study compact architectures, compression strategies, and reliable evaluation protocols for operational use.
References
Neural Elevation Models for Terrain Mapping and Path Planning
ImplicitTerrain: a Continuous Surface Model for Terrain Data Analysis
Motivation
Standard information retrieval systems optimize purely for relevance, yet consistently expose certain groups to disparate visibility, a form of algorithmic bias that has real-world consequences in job searches, product discovery, and beyond. The fair-reranker aims to integrate fairness constraints directly into a dense reranking pipeline, processing datasets such as BIOS (occupational bias), ESCI (e-commerce search), and TREC Fair Ranking.
Task
Develop an intersectional fair reranking DL model
Motivation
Consistent and reproducible evaluation enables research advancements. While CrisisFACTs presents a unique challenge in the current retrieval landscape, its evaluation needs to be reconsidered from the ground up to support new research efforts. The objective of the task is to select relevant texts for crisis operators and then create concise summaries. Currently, the evaluation relies on humans, which is impractical for testing any new model.
Task
The thesis aims to develop a new evaluation system and replicate previous solutions to establish a new working benchmark.
References
CrisisFACTS: Building and Evaluating Crisis Timelines