← Search

David Hartmann

2 accepted papers

2025

Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective

ICML 2025poster

The Abstraction and Reasoning Corpus (ARC-AGI) poses a significant challenge for large language models (LLMs), exposing limitations in their abstract reasoning abilities. In this work, we leverage task-specific data augmentations throughout the training, generation, and scoring phases, and employ a…

Cited by 0SourcePDFScholar
2021

Ringing ReLUs: Harmonic Distortion Analysis of Nonlinear Feedforward Networks

ICLR 2021poster

In this paper, we apply harmonic distortion analysis to understand the effect of nonlinearities in the spectral domain. Each nonlinear layer creates higher-frequency harmonics, which we call "blueshift", whose magnitude increases with network depth, thereby increasing the “roughness” of the output l…

Cited by 12SourcePDFScholar