相关论文: Exploring Transferable Homogeneous Groups for Comp…

Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts.…

Representing urban regions accurately and comprehensively is essential for various urban planning and analysis tasks. Recently, with the expansion of the city, modeling long-range spatial dependencies with multiple data sources plays an…

In this work, we introduce dual goal representations for goal-conditioned reinforcement learning (GCRL). A dual goal representation characterizes a state by "the set of temporal distances from all other states"; in other words, it encodes a…

Object recognition has become prevalent across various industries. However, most existing applications are limited to identifying objects alone, without considering their associated states. The ability to recognize both the state and object…

The key of referring expression comprehension lies in capturing the cross-modal visual-linguistic relevance. Existing works typically model the cross-modal relevance in each image, where the anchor object/expression and their positive…

Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by…

CDR (Cross-Domain Recommendation), i.e., leveraging information from multiple domains, is a critical solution to data sparsity problem in recommendation system. The majority of previous research either focused on single-target CDR (STCDR)…

Current research on tool learning primarily focuses on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness, a crucial factor in human problem-solving. In this paper, we address the selection…

Zero-Shot Learning (ZSL) has received extensive attention and successes in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. Key to ZSL is to transfer knowledge from the seen to the unseen…

We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of…

Self-supervised graph representation learning (SSGRL) is a representation learning paradigm used to reduce or avoid manual labeling. An essential part of SSGRL is graph data augmentation. Existing methods usually rely on heuristics commonly…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

Causal models provide rich descriptions of complex systems as sets of mechanisms by which each variable is influenced by its direct causes. They support reasoning about manipulating parts of the system and thus hold promise for addressing…

Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging task. We are exploring Open World Compositional Zero-Shot…

Representation steering offers a lightweight mechanism for controlling the behavior of large language models (LLMs) by intervening on internal activations at inference time. Most existing methods rely on a single global steering direction,…

Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in identifying…

Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art performance across wide-ranging domains. These methods' surprising…

Graph Transformers have recently achieved remarkable progress in graph representation learning by capturing long-range dependencies through self-attention. However, their quadratic computational complexity and inability to effectively model…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Interpretability plays a crucial role in the application of statistical learning to estimate heterogeneous treatment effects (HTE) in complex diseases. In this study, we leverage a rule-based workflow, namely causal rule learning (CRL), to…