XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
cs.LG, cs.AI
Submitted: 2026-01-29
Updated: 2026-11-11
Code: https://github.com/deepmind/3dshapes-dataset
Terminology
Sources
- Deep Variational Information Bottleneck
- Diffusion Visual Counterfactual Explanations
- Representation Learning: A Review and New Perspectives
- Isolating Sources of Disentanglement in Variational Autoencoders
- GANSpace: Discovering Interpretable GAN Controls
- Fader Networks: Manipulating Images by Sliding Attributes
- InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Supervised Contrastive Block Disentanglement
- Disentangled Information Bottleneck
- Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View
- The information bottleneck method
- On Disentangled Representations Learned From Correlated Data
- Representation Learning with Contrastive Predictive Coding
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
- DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
- Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis