Adrián Bazaga's Homepage
AI Research Scientist
Welcome to my website!
Research Interests:
My research is centered around advancing the capabilities of AI, particularly in the realms of multimodality and large language models. I aim to develop innovative architectures that can seamlessly integrate diverse data modalities to address both fundamental challenges and real-world problems 🧪. My current focus is on enhancing generative models, expanding their multimodal capabilities, refining new training methodologies, improving inference efficiency, and ensuring robustness and alignment. I am passionate about using AI to contribute to scientific discovery and am always open to collaborations that push the boundaries of what AI can achieve 👐.
Background:
I am a final-year Ph.D. student at the University of Cambridge, under the supervision of Prof. Pietro Liò and Prof. Gos Micklem. My academic journey began with a Bachelor’s in Computer Science, followed by a Master’s in Machine Learning. I have honed my research skills through internships at leading organizations like Microsoft Research and Amazon Science, where I worked in areas such as reasoning with Large Language Models and novel training schemes to improve few-step generation for diffusion models. Previously, I spent ∼5 years in various start-ups, working at the intersection of AI and medicine.
Beyond Research:
In addition to my core research, I am exploring how advancements in natural language processing, particularly generative models, can revolutionize education and governance. I am deeply committed to conducting research with a significant impact and am eager to engage in discussions and collaborations that align with these goals.
News
Sep 20, 2024 | [Paper] Our paper “HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs” has been accepted at EMNLP 2024 🎉 |
---|---|
Aug 15, 2024 | I joined Amazon Science AGI team as a Research Scientist Intern. Excited to work on reasoning with LLMs with Rexhina Blloshmi and Adrià de Gispert, in Berlin, Germany. ⭐ |
Aug 13, 2024 | I have accepted to serve as Reviewer for the International Conference on Learning Representations (ICLR). 👍 |
Jun 16, 2024 | Our paper “FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models” is now on arXiv. 📋 |
Jun 5, 2024 | [Paper] Our paper “TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting” has been accepted at ICML 2024 🎉 |
Jun 1, 2024 | I received a PhD Student Award by the Cambridge Society for the Application of Research in recognition of outstanding research with real world application, for my work on language-graph modality alignment for evidence retrieval. 🏅 |
May 1, 2024 | I joined Microsoft Research as a Research Scientist Intern. Thrilled to embark on this exciting journey, working on generative modeling (diffusion models) with Javier Zazo, Richard Turner and Ted Meeds, as well as the fantastic team at Cambridge, UK. ⭐ |
Mar 16, 2024 | [Paper] Our paper “Language Model Knowledge Distillation for Efficient Question Answering in Spanish” has been accepted at ICLR 2024 🎉 |
Mar 6, 2024 | [Paper] Our paper “Unsupervised Pretraining for Fact Verification by Language Model Distillation” has been accepted at ICLR 2024 🎉 |
Feb 15, 2024 | I was granted “Visiting Student” status in the Computer Science & Technology department under Pietro Liò´s group. I’m working on tabular LLMs to improve small tabular classification problems and LLMs for modeling partial differential equations 🚀 |