5 papers
A non-ergodic framework for understanding emergent capabilities in Large Language Models
Javier Marín
Large language models have emergent capabilities that come unexpectedly at scale, but we need a theoretical framework to explain why and how they emerge. We prove that language mod…
Hamiltonian Neural Networks for Robust Out-of-Time Credit Scoring
Javier Marín
This paper presents a novel credit scoring approach using neural networks to address class imbalance and out-of-time prediction challenges. We develop a specific optimizer and loss…
Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMs
Javier Marin
This paper proposes a novel approach to analyzing multi-hop reasoning in language models through Hamiltonian mechanics. We map reasoning chains in embedding spaces to Hamiltonian s…
Symmetries, Scaling Laws and Phase Transitions in Consumer Advertising Response
Javier Marin
Understanding how consumers respond to business advertising efforts is essential for optimizing marketing investment. This research introduces a new modeling approach based on the…
A new framework for Marketing Mix Modeling: Addressing Channel Influence Bias and Cross-Channel Effects
Javier Marin
This research addresses two fundamental challenges in Marketing Mix Modeling: the tendency of models to over-attribute influence to high-investment channels and the difficulty in q…