相关论文: JEPA for RL: Investigating Joint-Embedding Predict…

Precise robotic manipulation skills are desirable in many industrial settings, reinforcement learning (RL) methods hold the promise of acquiring these skills autonomously. In this paper, we explicitly consider incorporating operational…

Joint Embedding Predictive Architectures (JEPA) offer a promising approach to self-supervised speech representation learning, but suffer from representation collapse without explicit grounding. We propose GMM-Anchored JEPA, which fits a…

While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoders used are…

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A popular recent approach involves training a world model from state-action…

Existing methods for self-supervised representation learning of geospatial regions and map entities rely extensively on the design of pretext tasks, often involving augmentations or heuristic sampling of positive and negative pairs based on…

Fine-tuning Video Diffusion Models (VDMs) at the user level to generate videos that reflect specific attributes of training data presents notable challenges, yet remains underexplored despite its practical importance. Meanwhile, recent work…

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

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…

Embedding-based methods have attracted increasing attention in recent entity alignment (EA) studies. Although great promise they can offer, there are still several limitations. The most notable is that they identify the aligned entities…

In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…

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…

Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain…

The recent focus and release of pre-trained models have been a key components to several advancements in many fields (e.g. Natural Language Processing and Computer Vision), as a matter of fact, pre-trained models learn disparate latent…

Individualized manufacturing is becoming an important approach as a means to fulfill increasingly diverse and specific consumer requirements and expectations. While there are various solutions to the implementation of the manufacturing…

Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications. However, it still suffers from some key limits slowing down its widespread adoption. Its performance is sensitive to initial…

Aiming to produce reinforcement learning (RL) policies that are human-interpretable and can generalize better to novel scenarios, Trivedi et al. (2021) present a method (LEAPS) that first learns a program embedding space to continuously…

Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target…

We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether…

Data-efficient reinforcement learning (RL) in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. We consider a particularly important instance of this…