- vision
- language
- time series
- multimodal
- embedded
- internship
- thesis
•
•
•
•
•
•
-
LLM Agents for Automated Extraction of Supplier Pricing from Email Workflows
Design and prototyping of an agentic system for acquiring product costs from suppliers using LLM-based agents
-
Modular Mixture of Experts for Multi-Sensor Remote Sensing
Designing and benchmarking a plugin-style MoE architecture with independent sensor-specific encoders for multi-sensor remote sensing, as an alternative to monolithic foundation models.
-
Unsupervised Alignment of Geo-Embeddings for Rapid Disaster Mapping
Learning to align pre-computed geospatial embeddings with post-event satellite features for unsupervised disaster delineation without bi-temporal inference.
-
Graph Neural Networks for Street-Level Urban Temperature Mapping from Satellite Data
Development of a GNN-based architecture operating on satellite imagery, urban topology, and meteorological data to predict neighborhood-scale temperature distributions.
-
Efficient Adaptation of Vision–Language Models for Artistic Metadata Generation
This thesis involves specializing Vision–Language Models (VLMs) for multimodal artistic metadata generation through parameter-efficient fine-tuning and knowledge distillation approaches.