Related papers: Sub-JEPA: Subspace Gaussian Regularization for Sta…

Gaussian process latent variable models (GPLVMs) are a versatile family of unsupervised learning models commonly used for dimensionality reduction. However, common challenges in modeling data with GPLVMs include inadequate kernel…

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in…

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.…

Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have shown prior success, but lack robust geometric information that…

Self-supervised learning has emerged as a major technique for the task of learning from unlabeled data, where the current methods mostly revolve around alignment of representations and input recon struction. Although such approaches have…

Deep Learning based Weather Prediction (DLWP) models have been improving rapidly over the last few years, surpassing state of the art numerical weather forecasts by significant margins. While much of the optimization effort is focused on…

Quantifying the impacts of anthropogenic global warming requires accurate Earth system model (ESM) simulations. Statistical bias correction and downscaling can be applied to reduce errors and increase the resolution of ESMs. However,…

Optimal computations under uncertainty require an adequate probabilistic representation about beliefs. Deep generative models, and specifically Variational Autoencoders (VAEs), have the potential to meet this demand by building latent…

Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is…

This paper studies the fundamental problem of learning multi-layer generator models. The multi-layer generator model builds multiple layers of latent variables as a prior model on top of the generator, which benefits learning complex data…

World models, which simulate environmental dynamics and generate sensor observations, are gaining increasing attention in autonomous driving. However, progress in LiDAR-based world models has lagged behind those built on camera videos or…

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

In common real-world robotic operations, action and state spaces can be vast and sometimes unknown, and observations are often relatively sparse. How do we learn the full topology of action and state spaces when given only few and sparse…

The cornerstone of cognitive intelligence lies in extracting hidden patterns from observations and leveraging these principles to systematically predict future outcomes. However, current image tokenization methods demonstrate significant…

In federated learning, Transformer, as a popular architecture, faces critical challenges in defending against gradient attacks and improving model performance in both Computer Vision (CV) and Natural Language Processing (NLP) tasks. It has…

Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of large models by decomposing weight updates into low-rank matrices, significantly reducing storage and computational overhead. While effective, standard LoRA lacks…

The embedding-based representation learning is commonly used in deep learning recommendation models to map the raw sparse features to dense vectors. The traditional embedding manner that assigns a uniform size to all features has two…

Bayesian optimisation in the latent space of a Variational AutoEncoder (VAE) is a powerful framework for optimisation tasks over complex structured domains, such as the space of scientifically interesting molecules. However, existing…

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…

Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-frequency changes of keypoints), is essential for video-based…