相关论文: Learning to Extrapolate to New Tasks: A Relational…

The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory…

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence…

The existing supervised relation extraction methods have achieved impressive performance in a closed-set setting, where the relations during both training and testing remain the same. In a more realistic open-set setting, unknown relations…

Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem of multi-task…

Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these…

Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past knowledge. Many approaches address the problem by expanding the structure of a shared neural network as tasks arrive, but…

Class-incremental learning is dedicated to the development of deep learning models that are capable of acquiring new knowledge while retaining previously learned information. Most methods focus on balanced data distribution for each task,…

Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To…

We consider the problem of reward learning for temporally extended tasks. For reward learning, inverse reinforcement learning (IRL) is a widely used paradigm. Given a Markov decision process (MDP) and a set of demonstrations for a task, IRL…

This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learning of multiple…

Mixture-of-experts (MoE) architecture has been proven a powerful method for diverse tasks in training deep models in many applications. However, current MoE implementations are task agnostic, treating all tokens from different tasks in the…

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Understanding how agents learn to generalize -- and, in particular, to extrapolate -- in high-dimensional, naturalistic environments remains a challenge for both machine learning and the study of biological agents. One approach to this has…

We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In…

Multimedia applications often require concurrent solutions to multiple tasks. These tasks hold clues to each-others solutions, however as these relations can be complex this remains a rarely utilized property. When task relations are…

Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies,…

Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instances. To this end, we…

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…

We present the architecture and the evaluation of a new system for recognizing textual entailment (RTE). In RTE we want to identify automatically the type of a logical relation between two input texts. In particular, we are interested in…

Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge. In this paper, we focus on models that can learn manipulation…