Related papers: ACT-JEPA: Novel Joint-Embedding Predictive Archite…
This work introduces JEMA (Joint Embedding with Multimodal Alignment), a novel co-learning framework tailored for laser metal deposition (LMD), a pivotal process in metal additive manufacturing. As Industry 5.0 gains traction in industrial…
Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current…
Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…
Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-RL methods require partially or fully on-policy data, i.e.,…
High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…
Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously…
Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage. Most…
Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon…
Students in online courses generate large amounts of data that can be used to personalize the learning process and improve quality of education. In this paper, we present the Latent Skill Embedding (LSE), a probabilistic model of students…
Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator…
Graph Neural Networks (GNNs) have shown promise in learning dynamic functional connectivity for distinguishing phenotypes from human brain networks. However, obtaining extensive labeled clinical data for training is often…
Recent successes in self-supervised learning (SSL) model spatial co-occurrences of visual features either by masking portions of an image or by aggressively cropping it. Here, we propose a new way to model spatial co-occurrences by aligning…
Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents forgetting, it…
Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency…
Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform…
Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…
Offline Imitation Learning (IL) methods such as Behavior Cloning are effective at acquiring complex robotic manipulation skills. However, existing IL-trained policies are confined to executing the task at the same speed as shown in…
Joint-Embedding Self Supervised Learning (JE-SSL) has seen a rapid development, with the emergence of many method variations but only few principled guidelines that would help practitioners to successfully deploy them. The main reason for…
Despite its rise as a prominent solution to the data inefficiency of today's machine learning models, self-supervised learning has yet to be studied from a purely multi-agent perspective. In this work, we propose that aligning internal…
Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages,…