141 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Harbin Institute of TechnologyCN32 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- University of LjubljanaSI3 papers
- Dalian University of TechnologyCN2 papers
- Heilongjiang UniversityCN2 papers
- Institut de Recherche Mathématique AvancéeFR2 papers
- Jiaxing UniversityCN2 papers
- National Tsing Hua UniversityTW2 papers
- Université de StrasbourgFR2 papers
- Yanbian UniversityCN2 papers
- American Institute of Aeronautics and AstronauticsUS1 paper
- Anhui Science and Technology UniversityCN1 paper
43 papers
Curriculum reinforcement learning with measurable task representation learning
Yongyan Wen, Siyuan Li, Mingjian Fu +3
In curriculum reinforcement learning (CRL), an agent incrementally accumulates knowledge over a sequence of tasks (i.e., a curriculum), and the learning process is aimed at using t…
Full-gap kinetic limitation of thermionic-electron transport for electron transpiration cooling
Wushun Zhang, Weixing Zhou, Yinjian Zhao
Electron transpiration cooling (ETC) can reduce aerothermal loads on sharp hypersonic leading edges, but its performance is governed by whether thermionically emitted electrons esc…
ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architectures
Zhonghao Yang, Cheng Luo, Daojing He +2
Backdoor attacks pose a significant threat to the security and reliability of deep learning models. To mitigate such attacks, one promising approach is to learn to extract features…
Polynomials and asymptotic constants in a resurgent problem from 't Hooft
David Broadhurst, Gergő Nemes
In a recent study of the quantum theory of harmonic oscillators, Gerard 't Hooft proposed the following problem: given for , find its a…
Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs
Xiao Xu, Libo Qin, Wanxiang Che +1
Two-Tower Vision--Language Models (VLMs) have demonstrated strong performance across various downstream VL tasks. While BridgeTower further enhances performance by building bridges…
Asymptotic expansions for the generalised trigonometric integral and its zeros
Gergő Nemes
In this paper, we investigate the asymptotic properties of the generalised trigonometric integral and its associated modulus and phase functions for la…
Valley-dependent topological edge states in plasma photonic crystals
Jianfei Li, Chen Zhou, Jingfeng Yyao +5
Plasma photonic crystals designed in this paper are composed of gas discharge tubes to control the flow of electromagnetic waves. The band structures calculated by the finite eleme…
On the impact of spatial heterogeneity and drift rate in a three-patch two-species Lotka-Volterra competition model over a stream
Shanshan Chen, Jie Liu, Yixiang Wu
In this paper, we study a three-patch two-species Lotka-Volterra competition patch model over a stream network. The individuals are subject to both random and directed movements, a…
Stable solid molecular hydrogen above 900K from a machine-learned potential trained with diffusion Quantum Monte Carlo
Hongwei Niu, Yubo Yang, Scott Jensen +3
We survey the phase diagram of high-pressure molecular hydrogen with path integral molecular dynamics using a machine-learned interatomic potential trained with Quantum Monte Carlo…
An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development
Jin Yang, Guangxin Jiang, Yinan Wang +1
Recent years have witnessed exponential growth in developing deep learning (DL) models for time-series electricity forecasting in power systems. However, most of the proposed model…
Dynamic Relation Repairing for Knowledge Enhancement
Rui Kang, Hongzhi Wang
Dynamic relation repair aims to efficiently validate and repair the instances for knowledge graph enhancement (KGE), where KGE captures missing relations from unstructured data and…
On a class of Hessian type equations on Riemannian manifolds
Heming Jiao, Jinxuan Liu
In this paper, we consider a class of Hessian type equations which include the Monge-Ampère equation on Riemannian manifolds. The \emph{a priori} estimates and the ex…
Loeb Extension and Loeb Equivalence II
Duanmu Haosui, David Schrittesser, William Weiss
The paper answers two open questions that were raised in by Keisler and Sun. The first question asks, if we have two Loeb equivalent spaces and $(Ω, \mathcal G…
Local Patch Network with Global Attention for Infrared Small Target Detection
Fang Chen, Chenqiang Gao, Fangcen Liu +4
Infrared small target detection plays an important role in the infrared search and tracking applications. In recent years, deep learning techniques were introduced to this task and…
Deep Joint Source-Channel Coding for Multi-Task Network
Mengyang Wang, Zhicong Zhang, Jiahui Li +2
Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not…
BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
Haoyu Song, Yan Wang, Kaiyan Zhang +2
Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still ba…
Revisiting the third-order elastic constants of diamond: the higher-order effect
Mingqing Liao, Yong Liu, Yi Wang +7
In this letter, we study the higher-order effect on the third-order elastic constants (TOECs) of diamond using longitudinal stress-uniaxial strain (LSUS) approach based on density…
Abnormal topological refraction into free medium at sub-wavelength scale in valley phononic crystal plates
Linyun Yang, Kaiping Yu, Bernard Bonello +2
In this work we propose a topological valley phononic crystal plate and we extensively investigate the refraction of valley modes into the surrounding homogeneous medium. This phon…
Profile Consistency Identification for Open-domain Dialogue Agents
Haoyu Song, Yan Wang, Wei-Nan Zhang +3
Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how…
Lightweight image super-resolution with enhanced CNN
Chunwei Tian, Ruibin Zhuge, Zhihao Wu +4
Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amo…
Designing and Training of A Dual CNN for Image Denoising
Chunwei Tian, Yong Xu, Wangmeng Zuo +3
Deep convolutional neural networks (CNNs) for image denoising have recently attracted increasing research interest. However, plain networks cannot recover fine details for a comple…
Existence and multiplicity of solutions for fractional Schrödinger-Kirchhoff equations with Trudinger-Moser nonlinearity
Mingqi Xiang, Binlin Zhang, Dušan Repovš
We study the existence and multiplicity of solutions for a class of fractional Schrödinger-Kirchhoff type equations with the Trudinger-Moser nonlinearity. More precisely, we consid…
Qubit-assisted squeezing of the mirror motion in a dissipative optomechanical cavity system
Cheng-Hua Bai, Dong-Yang Wang, Shou Zhang +1
We investigate a hybrid system consisting of an atomic ensemble trapped inside a dissipative optomechanical cavity assisted with the perturbative oscillator-qubit coupling. It is s…
Sample-Efficient Policy Learning based on Completely Behavior Cloning
Qiming Zou, Ling Wang, Ke Lu +1
Direct policy search is one of the most important algorithm of reinforcement learning. However, learning from scratch needs a large amount of experience data and can be easily pron…