1k citations · 2.2k across the 35 of their papers we have counts for
7 papers · 1 filter
Application-Driven Exascale: The JUPITER Benchmark Suite
Andreas Herten, Sebastian Achilles, Damian Alvarez +28
Benchmarks are essential in the design of modern HPC installations, as they define key aspects of system components. Beyond synthetic workloads, it is crucial to include real appli…
Inverse Deep Learning Ray Tracing for Heliostat Surface Prediction
Jan Lewen, Max Pargmann, Mehdi Cherti +3
Concentrating Solar Power (CSP) plants play a crucial role in the global transition towards sustainable energy. A key factor in ensuring the safe and efficient operation of CSP pla…
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
Tomer Porian, Mitchell Wortsman, Jenia Jitsev +2
Kaplan et al. and Hoffmann et al. developed influential scaling laws for the optimal model size as a function of the compute budget, but these laws yield substantially different pr…
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis +56
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…
Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti +1
Large Language Models (LLMs) are often described as instances of foundation models that possess strong generalization obeying scaling laws, and therefore transfer robustly across v…
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham +2
Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the en…