9 citations · 18 across the 4 of their papers we have counts for
4 papers
Generating Chest X-Ray Counterfactuals by Specialising Foundation Image Models
Xiaodan Xing, Rajat R. Rasal, Julia A. Meister +3
Counterfactual image generation answers questions about how a subject would have looked under retrospective, hypothetical scenarios. Recent methods have improved perceptual quality…
Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability
Luca Baroni, Galvin Khara, Joachim Schaeffer +2
Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its r…
Robust image representations with counterfactual contrastive learning
Mélanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia +2
Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the d…
Counterfactual contrastive learning: robust representations via causal image synthesis
Melanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia +2
Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice…