Chengjian Li,Xiangbo Shu,Qiongjie Cui et al.
Chengjian Li et al.
Text-driven diffusion models have achieved remarkable performance in human motion generation. However, these generative works struggle to generate high-quality motion consistent with textual descriptions. The primary reasons are: 1) insuffi...
Chang Nie,Tianchen Deng,Zhe Liu et al.
Chang Nie et al.
Denoising is important in many vision, medical, and biological applications, yet real observations are often corrupted by complex nonlinear noise and clean targets are often unavailable. We present MID, a self-supervised iterative denoising...
XAI-Exit: Interpretability-Driven Dynamic Early Exits for Efficient and Transparent DNN Inference [0.03%]
透明高效的深度神经网络动态早退出推理方法
Haseena Rahmath P,Ajith Abraham,Kuldeep Chaurasia
Haseena Rahmath P
Deep neural networks (DNNs) excel across domains but face challenges in resource-constrained and critical settings due to high computational cost and limited transparency. Early exit DNNs reduce overhead via intermediate predictions; yet, m...
Multiscale Convolutional Stochastic Configuration Network Soft Sensor Modeling Method [0.03%]
多尺度卷积型随机配置网络软测量方法
Aijun Yan,Chunpeng Yang
Aijun Yan
To address the challenges of industrial process modeling caused by multiscale spatiotemporal coupling, a soft sensor method based on the multiscale convolutional stochastic configuration network (MSC-SCN) is proposed. This method introduces...
End-to-End Image Compression With Segmentation Guided Dual Coding for Wind Turbines [0.03%]
用于风力涡轮机的分割引导双重编码端到端图像压缩方法
Raul Perez-Gonzalo,Andreas Espersen,Soren Forchhammer et al.
Raul Perez-Gonzalo et al.
Transferring large volumes of high-resolution images during wind turbine inspections introduces a bottleneck in assessing and detecting severe defects. Efficient coding must preserve high fidelity in blade regions while aggressively compres...
Human-Machine Co-Adaptation for Robot-Assisted Rehabilitation via Dual-Agent Multiple Model Reinforcement Learning (DAMMRL) [0.03%]
基于双智能体多模型强化学习的康复机器人辅助训练中的主从双向适应方法 دمش
Yang An,Yaqi Li,Hongwei Wang et al.
Yang An et al.
This study introduces a novel approach to robot-assisted ankle rehabilitation by proposing a dual-agent multiple model reinforcement learning (DAMMRL) framework, leveraging multiple model adaptive control (MMAC) and co-adaptive control stra...
Yueen Ma,Zixing Song,Yuzheng Zhuang et al.
Yueen Ma et al.
Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and v...
Dual-Path Conditional Diffusion Model With Attribute Consistency for Zero-Shot Fault Diagnosis [0.03%]
基于属性一致性的双路径条件扩散模型的零样本故障诊断方法
Wenjie Liao,Like Wu,Shihui Xu et al.
Wenjie Liao et al.
In traditional data-driven fault diagnosis, acquiring training examples for all potential fault classes is highly challenging. Zero-shot learning (ZSL) methods based on generative adversarial networks (GANs) have shown promising results; ho...
Monte Carlo Marginalization: A Differentiable Method to Learn High-Dimensional Distributions [0.03%]
蒙特卡洛边际化：一种学习高维分布的可微方法
Chenqiu Zhao,Guanfang Dong,Anup Basu
Chenqiu Zhao
Learning intractable distributions in high-dimensional spaces remains a fundamental challenge. While prevalent deep learning methods often rely on restrictive prior assumptions, we propose a novel differentiable method that approximates int...
Motif-Based Hypergraph Representation Learning: Transductive and Inductive Inference for Gene Regulatory Networks [0.03%]
基于基序的超图表示学习：基因调控网络中的推断问题研究
Songyang Wu,Mingjing Tang,Tong Zi et al.
Songyang Wu et al.
Network motifs, as fundamental functional substructures in gene regulatory networks (GRNs), play a critical role in regulating gene expression. Despite the successful application of graph representation learning in GRN modeling, most existi...