Related papers: CARLS: Cross-platform Asynchronous Representation …

We present a system for training enterprise search agents via reinforcement learning that achieves state-of-the-art performance across a diverse suite of hard-to-verify agentic search tasks. Our work makes four core contributions. First, we…

Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and…

Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given modelling task. While various deep learning approaches have…

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…

Human-driven vehicles (HVs) exhibit complex and diverse behaviors. Accurately modeling such behavior is crucial for validating Robot Vehicles (RVs) in simulation and realizing the potential of mixed traffic control. However, existing…

The performance of deep learning models highly depends on the amount of training data. It is common practice for today's data holders to merge their datasets and train models collaboratively, which yet poses a threat to data privacy.…

Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL). They are designed to control how a DRL agent collects data, which is…

Complementary Learning Systems (CLS) theory suggests that the brain uses a 'neocortical' and a 'hippocampal' learning system to achieve complex behavior. These two systems are complementary in that the 'neocortical' system relies on slow…

Recent self-supervised learning approaches focus on using a few thousand data points to learn policies for high-level, low-dimensional action spaces. However, scaling this framework for high-dimensional control require either scaling up the…

Transfer learning eases the burden of training a well-performed model from scratch, especially when training data is scarce and computation power is limited. In deep learning, a typical strategy for transfer learning is to freeze the early…

Building robust and real-time classifiers with diverse datasets are one of the most significant challenges to deep learning researchers. It is because there is a considerable gap between a model built with training (seen) data and real…

Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, leading to suboptimal learning. We propose Collaborative…

Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay…

We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code…

Recent advancements in generative models have established state-of-the-art benchmarks in the generation of molecules and novel drug candidates. Despite these successes, a significant gap persists between generative models and the…

Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding, and is already established as a critical modality in remote sensing. However, variability in channel dimensionality and…

This paper introduces CARSS (Cooperative Attention-guided Reinforcement Subpath Synthesis), a novel approach to address the Traveling Salesman Problem (TSP) by leveraging cooperative Multi-Agent Reinforcement Learning (MARL). CARSS…

Self-supervised learning on graphs has made large strides in achieving great performance in various downstream tasks. However, many state-of-the-art methods suffer from a number of impediments, which prevent them from realizing their full…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Active learning (AL) is a learning paradigm where an active learner has to train a model (e.g., a classifier) which is in principal trained in a supervised way, but in AL it has to be done by means of a data set with initially unlabeled…