Welcome
Welcome to my Website! I’m Miquel, currently pursuing my PhD at Northeastern University. My research revolves around the dynamic field of telecomms, where I’m deeply engaged in exploring the applications of Machine Learning and Artificial Intelligence. Join me on this exciting journey as we delve into the future of technology, including the promising realm of 6G and beyond. Don’t hesitate to connect with me on LinkedIn or at sirera.m@northeastern.edu if you find our work intriguing, wish to explore collaboration opportunities, or if you have any inquiries. Let’s work together to shape the next generation of telecommunications!
Education
Universitat Politècnica de Catalunya | BSc on Data Science | 2019 - 2023
Northeastern University | PhD on Computer Engineering | 2024 - Current
Experience
Abi Global Health | AI Engineer intern | 2022
Northeastern University | UG Research Assistant | 2023
Current projects
- Distributed Large Language Models inference in challenging environments
We are actively building upon the JARVIS project—a distributed framework for Large Language Models (LLMs) that intelligently partitions model layers across edge devices with constrained computational resources. Read the original paper in My Research.
JARVIS introduces enhanced resilience to node failures through peer-to-peer communication and layer redundancy, ensuring reliable performance even in challenging conditions. We evaluated this framework with Google’s Gemma LLM (2B parameters), deploying it on 18 software-defined radios in the NSF Colosseum RF emulator and a 7-node Raspberry Pi testbed.
Our results demonstrate JARVIS’s robustness in tactical environments, achieving an optimal balance between computation and communication for real-world applications.
- Neural Point Processes for Pixel-wise Regression
In this project we address the challenge of pixel-wise regression problems with sparsely annotated images. Traditional methods struggle with unlabeled areas, leading to distorted predictions. We introduce Neural Point Processes, combining 2D Gaussian Processes with neural networks to leverage spatial correlations between sparse labels. Our method significantly improves mean-squared error and \(R^{2}\) scores, outperforming standard regression techniques across both real-world and synthetic datasets.
- Extension of Communication-Aware DNN Pruning
In this project, we extend the work on communication-aware deep neural network (DNN) pruning. We focus on training networks to be deployed in a distributed fashion, reducing the need for information exchange while maintaining high accuracy. This approach aims to optimize network performance by balancing computational load and communication efficiency, ensuring robust deployment in distributed environments.