technique
Disentangled Representation Learning
techniqueactiveprovisional
disentangled-representation-learning-0f84f08b·1 events·first seen 21d agoAliases: Disentangled Representation Learning
Co-occurring entities
More like this (12)
Disentangled RNNsMatryoshka Representation Learningmultivariate time series representation learningdecoupled reinforcement learningRelational Deep LearningDeng Representationlinear representation hypothesisThe Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language ModelRepresentational Similarity AnalysisAlternating Token-Weighted UnlearningBackdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMsshielded reinforcement learning
Recent events (1)
Representation-Conditioned Diffusion Models for Controllable Image Generation
This paper explores conditioning diffusion models on representations from pre-trained self-supervised models as an alternative to text prompts or semantic maps, which require large annotated datasets. The self-conditioning mechanism improves unconditional image generation quality and provides a controllable representation space. The authors identify directions of variation in this space and demonstrate smoothness and disentanglement properties, suggesting potential for fine-grained generative control without heavy annotation overhead.