Counterfactual Knowledge Distillation
PulseAugur coverage of Counterfactual Knowledge Distillation — every cluster mentioning Counterfactual Knowledge Distillation across labs, papers, and developer communities, ranked by signal.
-
New DiDAE method tackles foundation model vulnerabilities with faster counterfactuals
Researchers have introduced Disentangled Diffusion Autoencoders (DiDAE), a novel method designed to address vulnerabilities in foundation models, such as spurious correlations and "Clever Hans" strategies. DiDAE integra…
-
New Study: Counterfactual Fairness Doesn't Imply Group Fairness in Image Classification
A new study published on arXiv investigates the relationship between counterfactual fairness (CF) and group fairness (GF) in image classification. Researchers constructed new datasets, \oursceleb and \ourslfw, to evalua…
-
New DiDAE framework enables faster, scalable counterfactual generation for foundation models
Researchers have introduced Visual Disentangled Diffusion Autoencoders (DiDAE), a new framework designed to generate counterfactual data for foundation models. This method integrates disentangled dictionary learning wit…