Search Results for author:
Found 5 papers, 3 papers with code
Recovering the Pre-Fine-Tuning Weights of Generative Models
The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine-tuning.
Improving Zero-Shot Models with Label Distribution Priors
We propose a new approach, CLIPPR (CLIP with Priors), which adapts zero-shot models for regression and classification on unlabelled datasets.
Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors
Breaking from previous research, we present a new anomaly detection method that allows operators to exclude an attribute from being considered as relevant for anomaly detection.
A Contrastive Objective for Learning Disentangled Representations
Here, our objective is to learn representations that are invariant to the domain (sensitive attribute) for which labels are provided, while being informative over all other image attributes, which are unlabeled.
Inductive-Biases for Contrastive Learning of Disentangled Representations
Current discriminative approaches are typically based on adversarial-training and do not reach comparable accuracy.
