Sorry, you need to enable JavaScript to visit this website.

Visual Word Sense Disambiguation (Visual-WSD), as a subtask of fine-grained image-text retrieval, requires a high level of language-vision understanding to capture and exploit the nuanced relationships between text and visual features. However, the cross-linguistic background only with limited contextual information is considered the most significant challenges for this task.

Neural semantic parsing maps natural languages (NL) to equivalent formal semantics which are compositional and deduce the sentence meanings by composing smaller parts. To learn a well-defined semantics, semantic parsers must recognize small parts, which are semantic mappings between NL and semantic tokens. Attentions in recent neural models are usually explained as one-on-one semantic mappings. However, attention weights with end-to-end training are shown only weakly correlated with human-labeled mappings. Despite the usefulness, supervised mappings are expensive.

This paper proposes an efficient optimizer called AdaPlus which integrates Nesterov momentum and precise stepsize adjustment on AdamW basis. AdaPlus combines the advantages of AdamW, Nadam, and AdaBelief and, in particular, does not introduce any extra hyper-parameters. We perform extensive experimental evaluations on three machine learning tasks to validate the effectiveness of AdaPlus.

We propose a sampling algorithm to perform system identification from a set of input-output graph signal pairs. The dynamics of the systems we study are given by a partially known adjacency matrix and a generic parametric graph filter of unknown parameters. The methodology we employ is built upon the principles of annealed Langevin diffusion. This enables us to draw samples from the posterior distribution instead of following the classical approach of point estimation using maximum likelihood.

Protein representation learning is critical in various tasks in biology, such as drug design and protein structure or function prediction, which has primarily benefited from protein language models and graph neural networks. These models can capture intrinsic patterns from protein sequences and structures through masking and task-related losses. However, the learned protein representations are usually not well optimized, leading to performance degradation due to limited data, difficulty adapting to new tasks, etc.

Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an effective and fast approach that could balance the text-image consistency and identity consistency of the generated image and reference image. Our method can generate personalized images without any fine-tuning while maintaining the inherent text-to-image generation ability of diffusion models.

Recent RGBD trackers have employed cueing techniques by overlaying Depth modality images as cues onto RGB modality images, which are then fed into the RGB-based model for tracking. However, the direct overlaying interaction method between modalities not only introduces more noise into the feature space but also exhibits the inadaptability of the RGB-based model to mixed-modality inputs. To address these issues, we introduce Visual Adapt for RGBD Tracking (VADT). Specifically, we maintain the input of the RGB-based model as the RGB modality.

Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness by leveraging richer textual information in user profiles and job descriptions apart from user behavior features and job metadata. However, the general domain-oriented design struggles to capture the unique structural information within user profiles and job descriptions, leading to a loss of latent semantic correlations.

Prompt learning was proposed to solve the problem of inconsistency between the upstream and downstream tasks and has achieved State-Of-The-Art (SOTA) results in various Natural Language Processing (NLP) tasks. However, Relation Extraction (RE) is more complex than other text classification tasks, which makes it more difficult to design a suitable prompt template for each dataset manually. To solve this issue, we propose a Adaptive Prompt Construction method (APC) for relation extraction.

To date, research on relation mining has typically focused on analyzing explicit relationships between entities, while ignoring the underlying connections between entities, known as implicit relationships. Exploring implicit relationships can reveal more about social dynamics and potential relationships in heterogeneous social networks to better explain complex social behaviors. The research presented in this paper explores implicit relationships discovery methods in the context of heterogeneous social networks.