papers

Publications (14)

cs.AI2018

Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder

Junjie Zeng, Long Qin, Yue Hu +2

In this paper, we present a hierarchical path planning framework called SG-RL (subgoal graphs-reinforcement learning), to plan rational paths for agents maneuvering in continuous a…

cs.LG2025

Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification

Ming Hu, Jianfu Yin, Mingyu Dou +8

The automatic classification of medical time series signals, such as electroencephalogram (EEG) and electrocardiogram (ECG), plays a pivotal role in clinical decision support and e…

cond-mat.str-el2023

Correlated flat bands in the paramagnetic phase of triangular antiferromagnets NaBaX(PO) (X = Mn, Co, Ni)

Cong Hu, Xuefeng Zhang, Yunlong Su +1

Flat band systems in condensed matter physics are intriguing because they can exhibit exotic phases and unconventional properties. In this work, we studied three correlated magneti…

cs.CV2022

SDA-Net: Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation

Qingbei Guo, Xiao-Jun Wu, Zhiquan Feng +2

Existing multi-scale solutions lead to a risk of just increasing the receptive field sizes while neglecting small receptive fields. Thus, it is a challenging problem to effectively…

physics.chem-ph2019

Decoherence in Molecular Electron Spin Qubits: Insights from Quantum Many-Body Simulations

Jia Chen, Cong Hu, John F. Stanton +3

Quantum states are described by wave functions whose phases cannot be directly measured, but which play a vital role in quantum effects such as interference and entanglement. The l…

cs.CV2026

FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement

Ming Hu, Yongsheng Huo, Mingyu Dou +6

Fine-grained anomaly detection is crucial in industrial and medical applications, but labeled anomalies are often scarce, making zero-shot detection challenging. While vision-langu…

cs.CV2019

Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning

Cong Hu, Zhen-Hua Feng, Xiao-Jun Wu +1

To learn disentangled representations of facial images, we present a Dual Encoder-Decoder based Generative Adversarial Network (DED-GAN). In the proposed method, both the generator…

cond-mat.str-el2021

Reentrance of metal-insulator transition and magnetic competitions on a triangular lattice with second nearest-neighbor hopping

Xin Gao, Cong Hu, Jian Sun +3

The antiferromagnetism (AFM) is widely believed as the magnetic ground state of the triangular systems because of the geometrical frustration. The emergence of novel…

cs.CL2023

A Token-level Contrastive Framework for Sign Language Translation

Biao Fu, Peigen Ye, Liang Zhang +4

Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people. Recently, researchers have adopted Neural Machine…

cs.CV2026

WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing

Ming Hu, Mingyu Dou, Jianfu Yin +5

Recent one-step text-to-image (T2I) models enable efficient image synthesis and provide new opportunities for real-time image editing. However, existing one-step editing methods pr…

cs.CV2026

Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction

Yuanbo Li, Tianyang Xu, Cong Hu +3

With the rapid advancement and widespread application of vision-language pre-training (VLP) models, their vulnerability to adversarial attacks has become a critical concern. In gen…

cs.CV2026

Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models

Yuanbo Li, Tianyang Xu, Cong Hu +3

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversa…

math.CO2024

Second largest maximal cliques in small Paley graphs of square order

Huye Chen, Sergey Goryainov, Cong Hu

There is a conjecture that the second largest maximal cliques in Paley graphs of square order have size , where , and split into two or…

cs.CL2023

Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment

Rui Zhao, Liang Zhang, Biao Fu +3

Sign language translation (SLT) aims to convert continuous sign language videos into textual sentences. As a typical multi-modal task, there exists an inherent modality gap between…