DSReg: Provably Recovering Individual World Latents without Reconstruction

cs.LG, cs.AI, cs.RO, stat.ML

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: Project page: https://dsreg.github.io/

Code: https://github.com/deepmind/dsprites-dataset

Project page: https://dsreg.github.io/ABSTRACT

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Sparse Gaussian ICA
• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
• Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
• When Does LeJEPA Learn a World Model?
• Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
• Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• Causal Representation Learning Made Identifiable by Grouping of Observational Variables
• Causal Representation Learning from General Environments under Nonparametric Mixing
• Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
• Learning Temporally Causal Latent Processes from General Temporal Data

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks