Hacking Generative Models with Differentiable Network Bending
In this paper, we 'hack' generative models by injecting a small-scale trainable module between the intermediate layers of the model. This approach pushes their outputs away from the original training distribution towards a new objective.
Dec 1, 2023
*Towards data-driven models of hadronization
In this paper we present two novel training paradigm to ....
Dec 1, 2023
*Towards data-driven models of hadronization
In this paper we present two novel training paradigm to ....
Dec 1, 2023
FASST, Few-Shot Abstractive Summarization for Style Transfer
The paper introduces a novel unsupervised text style transfer method using few-shot abstractive summarization. This approach aligns vector space embeddings of source and target texts, selects nearest neighbors based on semantic similarity, and reranks the summarization. This method significantly improves style transfer quality and achieves soa results in automatic evaluation metrics.
Sep 1, 2023
*Earth mover’s distance as a measure of CP violation
In this paper, a novel unbinned test statistic based on the Wasserstein distance is introduced to detect charge conjugation parity (CP) symmetry violation, demonstrated with CP asymmetric distributions in B0 and D0 decays. This statistic matches the sensitivity of traditional tests while providing more detailed insights into localized CP asymmetry.
May 1, 2023
Normalizing Flows for Fragmentation and Hadronization
In this paper we present two novel training paradigm to ....
Dec 1, 2022
An example conference paper
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.
Jul 1, 2013