arXiv AI
Jul 22
RAMP: Recognition parametrisation by Amortised Message Passing
arXiv:2607. 18883v1 Announce Type: cross Abstract: A central aim of unsupervised learning is to uncover latent factors that explain dependencies among observations.
Hierarchical Latent Structure Learning through Online Inference
arXiv:2603. 19139v2 Announce Type: replace Abstract: Learning systems must balance generalization across experiences with discrimination of task-relevant details.
Related stories
arXiv Machine Learning
Jun 5
Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications
arXiv:2606. 06288v1 Announce Type: cross Abstract: Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements.
Hugging Face Trending Papers
Jul 29
Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method
Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning from pixels by regularizing the latent marginal distribution toward an isotropic Gaussian, thereby preventing representation collapse. While effective and elegant in single-task settings, this recipe does not extend reliably to multi-task training, leading to substantially worse downstream behavior-cloning performance.
arXiv Machine Learning
Jul 30
Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method
arXiv:2607. 26924v1 Announce Type: new Abstract: Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning from pixels by regularizing the latent marginal distribution toward an isotropic Gaussian, thereby preventing representation collapse.
arXiv Machine Learning
Jun 16
Structured Nonparametric Variational Inference for Dependent Latent Modeling
arXiv:2606. 15458v1 Announce Type: cross Abstract: Variational inference (VI) is a core engine of modern AI, enabling scalable approximate Bayesian learning and uncertainty-aware training of large probabilistic and generative models.
arXiv Machine Learning
Jun 19
Multi-Task Bayesian In-Context Learning
arXiv:2606. 20538v1 Announce Type: new Abstract: Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization.
arXiv Machine Learning
2d ago
The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning
arXiv:2608. 16245v1 Announce Type: new Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate.
arXiv Machine Learning
Jun 5
Zero-Flow Encoders
arXiv:2602. 00797v2 Announce Type: replace-cross Abstract: Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions.
arXiv AI
Jun 16
Adaptive inference and function vectors in deep transformers
arXiv:2606. 16694v1 Announce Type: cross Abstract: Transformers are widely used as a general-purpose substrate for learning complex correlations between a large collection of coupled variables, but their internal mechanisms have remained mysterious.
arXiv Machine Learning
Jun 29
Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation
arXiv:2606. 27681v1 Announce Type: new Abstract: World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based architectures predictive performance fails to reflect representation quality due to history bypass, rendering the latent state unidentifiable.
arXiv Machine Learning
Jun 8
Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients
arXiv:2606. 07400v1 Announce Type: new Abstract: Many scientific problems require inferring unobserved mechanistic latent states from indirect observations.
arXiv Machine Learning
Jul 7
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
arXiv:2607. 04409v1 Announce Type: new Abstract: Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making.