From the 1 of 14 linked papers with an AI index.
14 papers
From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs
Tina Vartziotis, Rodopi Kosteli, Elli Vartziotis +5
The paper introduces an analytical, calibrated method to estimate the energy consumption of large language model inference on NVIDIA H100 GPUs without direct power measurements, se…
Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves
Kartik Tandon, Julian Gould, Tanishq Bhatia +3
Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, probability distributions, or operat…
A Statistical Framework for Algorithmic Collective Action with Multiple Collectives
Claudio Battiloro, Pietro Greiner, Dario Rancati +3
As learning systems increasingly shape everyday decisions, Algorithmic Collective Action (ACA), i.e., users coordinating changes to shared data to steer model behavior, offers a co…
Guided Transfer Learning for Discrete Diffusion Models
Julian Kleutgens, Claudio Battiloro, Lingkai Kong +3
Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autoregressive modeling. Yet this perf…
Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding
Manuel Lecha, Andrea Cavallo, Francesca Dominici +5
Graph Neural Networks (GNNs) excel at learning from pairwise interactions but often overlook multi-way and hierarchical relationships. Topological Deep Learning (TDL) addresses thi…
Understanding Spatial Regression Models from a Weighting Perspective in an Observational Study of Superfund Remediation
Sophie M. Woodward, Francesca Dominici, Jose R. Zubizarreta
A key challenge in environmental health research is unmeasured spatial confounding, driven by unobserved spatially structured variables that influence both treatment and outcome. A…