Friends Links

Nevertheless, existing methods emphasize the design of elegant KGC models to facilitate modality interaction, neglecting the real-life problem of missing modalities in KGs.

Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs.

To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC).

In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.

We explore a setup for performing classification on labeled classical datasets, consisting of a classical neural network connected to a quantum annealer.

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.

However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test set.

Therefore, this study aims to explore the potential of FMs in the field of smart agriculture.

Experimental results on benchmark datasets demonstrate that our method achieves the State-Of-The-Art (SOTA) performance in terms of both image quality and inter-frame brightness consistency.

Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor.

Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers.

Note that we use LDCT images based on the noisy-as-clean strategy for corruption instead of NDCT images.

The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem.

It motivates us to develop a technique to evaluate true loss changes without retraining, with which channels to prune can be selected more reliably and confidently.

Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages.

Physics-Informed Neural Networks (PINNs) have gained popularity in solving nonlinear partial differential equations (PDEs) via integrating physical laws into the training of neural networks, making them superior in many scientific and engineering applications.

We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.

In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news.

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.

One of the challenges in learning to perform abstract reasoning is that problems are often posed as monolithic tasks, with no intermediate subgoals.

This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition.

Medical systematic reviews can be very costly and resource intensive.

Hyper-relational knowledge graph completion (HKGC) aims at inferring unknown triples while considering its qualifiers.

Email platforms need to generate personalized rankings of emails that satisfy user preferences, which may vary over time.

In this work, we propose a novel training mechanism termed SegPrompt that uses category information to improve the model's class-agnostic segmentation ability for both known and unknown categories.

Operations such as edge detection, image enhancement, and super-resolution, provide the foundations for higher level image analysis.

To overcome the above issues, we introduce CycleAdapt, which cyclically adapts two networks: a human mesh reconstruction network (HMRNet) and a human motion denoising network (MDNet), given a test video.

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to the outdated/noisy data.

State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e. g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR.

Many machine translation toolkits make use of a data preparation step wherein raw data is transformed into a tensor format that can be used directly by the trainer.