Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations

arXiv:2608.24762 · cs.LG, cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/deepmind/3dshapesdataset

Terminology

• Representation Learning — 7× in this paper · explained in 2 episodes
• Anisotropy — 6× in this paper · explained in 3 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Alberta Machine Intelligence Institute — 2× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Cooperation — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Disentangling Factors of Variation via Generative Entangling
• Hyperspherical Variational Auto-Encoders
• Constructing VAE Latent Spaces with Prescribed Topology

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks