2 papers
cs.LG2026
Trapped by simplicity: When Transformers fail to learn from noisy features
Evan Peters, Ando Deng, Matheus H. Zambianco +2
Noise is ubiquitous in data used to train large language models, but it is not well understood whether these models are able to correctly generalize to inputs generated without noi…
hep-th2025
Emergent metric from wavelet-transformed quantum field theory
Å imon Vedl, Daniel J. George, Fil Simovic +5
We introduce a method of reverse holography by which a bulk metric is shown to arise from locally computable multiscale correlations of a boundary quantum field theory (QFT). The m…