3 papers
cs.LG2024
Kernelized Concept Erasure
Shauli Ravfogel, Francisco Vargas, Yoav Goldberg +1
The representation space of neural models for textual data emerges in an unsupervised manner during training. Understanding how those representations encode human-interpretable con…
stat.ML2024
To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models
Francisco Vargas, Teodora Reu, Anna Kerekes +1
Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a di…
cs.LG2024
Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
Francisco Vargas, Ryan Cotterell
Bolukbasi et al. (2016) presents one of the first gender bias mitigation techniques for word representations. Their method takes pre-trained word representations as input and attem…