Related papers: A Lightweight Library for Energy-Based Joint-Embed…

This paper studies the fundamental problem of multi-layer generator models in learning hierarchical representations. The multi-layer generator model that consists of multiple layers of latent variables organized in a top-down architecture…

Epistemic Planning (EP) is an important research area dedicated to reasoning about the knowledge and beliefs of agents in multi-agent cooperative or adversarial settings. The Justified Perspective (JP) model is the state-of-the-art approach…

Autoencoder-based learning has emerged as a staple for disciplining representations in unsupervised and semi-supervised settings. This paper analyzes a framework for improving generalization in a purely supervised setting, where the target…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

We propose a learning algorithm to overcome the limitations of traditional backpropagation in resource-constrained environments: Solo Pass Embedded Learning Algorithm (SPELA). SPELA operates with local loss functions to update weights,…

Learning good feature embeddings for images often requires substantial training data. As a consequence, in settings where training data is limited (e.g., few-shot and zero-shot learning), we are typically forced to use a generic feature…

Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty. Despite recent advances, training EBMs on high-dimensional data remains a challenging problem as the state-of-the-art approaches are costly, unstable,…

In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over…

Performance modeling is an essential tool in many areas, including performance characterization/optimization, design space exploration, and resource allocation problems, to name a few. However, existing performance modeling approaches have…

Agents navigating in 3D environments require some form of memory, which should hold a compact and actionable representation of the history of observations useful for decision taking and planning. In most end-to-end learning approaches the…

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…

Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new tasks may not align well with the updates suitable for older…

Learning in the brain is poorly understood and learning rules that respect biological constraints, yet yield deep hierarchical representations, are still unknown. Here, we propose a learning rule that takes inspiration from neuroscience and…

Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-can substantially accelerate training and improve generation…

Classical models for supervised machine learning, such as decision trees, are efficient and interpretable predictors, but their quality is highly dependent on the particular choice of input features. Although neural networks can learn…

Current approaches to memory in neural systems rely on similarity-based retrieval: given a query, find the most representationally similar stored state. This assumption -- that useful memories are similar memories -- fails to capture a…

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Meta-learning algorithms adapt quickly to new tasks that are drawn from the same task distribution as the training tasks. The mechanism leading to fast adaptation is the conditioning of a downstream predictive model on the inferred…

In this work, we present a learning-based pipeline to realise local navigation with a quadrupedal robot in cluttered environments with static and dynamic obstacles. Given high-level navigation commands, the robot is able to safely locomote…

Deep subspace clustering has attracted increasing attention in recent years. Almost all the existing works are required to load the whole training data into one batch for learning the self-expressive coefficients in the framework of deep…