papers

Publications (19)

cs.CV2024

Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID

De Cheng, Lingfeng He, Nannan Wang +3

Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to match pedestrian images of the same identity from different modalities without annotations. Existing wo…

cond-mat.str-el2022

Thermal Energy Transport in Oxide Nuclear Fuel

David H. Hurley, Anter El-Azab, Matthew S. Bryan +13

To efficiently capture the energy of the nuclear bond, advanced nuclear reactor concepts seek solid fuels that must withstand unprecedented temperature and radiation extremes. In t…

cs.CV2025

Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification

Haonan Shi, Yubin Wang, De Cheng +3

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to learn modality-invariant image features from unlabeled cross-modal person datasets by reducing the modali…

cs.LG2026

Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning

Lingfeng He, De Cheng, Huaijie Wang +3

Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Effici…

cond-mat.mtrl-sci2025

Xenon-metal pair formation in UO2 investigated using DFT+U

Linu Malakkal, Shuxiang Zhou, Himani Mishra +4

A recent experimental study on a spent uranium dioxide (UO2) fuel sample from Belgium Reactor 3 (BR3) identified a unique pair structure formed by the noble metal phase (NMP) and f…

cs.CV2024

Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement

De Cheng, Xiaojian Huang, Nannan Wang +3

Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial f…

cs.CV2025

StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning

Huaijie Wang, De Cheng, Guozhang Li +5

Video Class-Incremental Learning (VCIL) seeks to develop models that continuously learn new action categories over time without forgetting previously acquired knowledge. Unlike tra…

cond-mat.mtrl-sci2025

Phase-field modeling of radiation-induced composition redistribution: An application to additively manufactured austenitic Fe-Cr-Ni

Sourabh Bhagwan Kadambi, Daniel Schwen, Jia-Hong Ke +2

Multicomponent alloys undergoing irradiation damage develop radiation-induced composition redistribution at point defect sinks such as grain boundaries (GBs) and dislocations. Such…

cs.CV2025

CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning

Lingfeng He, De Cheng, Zhiheng Ma +4

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered incre…

cond-mat.mtrl-sci2025

Engineering Phonons in Compositionally Complex Carbide Ceramics

Linu Malakkal, Jarin C French, Lanh Trinh +6

In the pursuit of advanced ceramic materials with exceptional irradiation-resistance and high-temperature tolerance for nuclear applications, compositionally complex carbides (CCCs…

cs.CV2025

R-Genie: Reasoning-Guided Generative Image Editing

Dong Zhang, Lingfeng He, Rui Yan +2

While recent advances in image editing have enabled impressive visual synthesis capabilities, current methods remain constrained by explicit textual instructions and limited editin…

cs.CV2025

Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning

De Cheng, Yue Lu, Lingfeng He +4

Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge. Recently, State Space Mode…

cond-mat.mes-hall2021

Training artificial neural networks for precision orientation and strain mapping using 4D electron diffraction datasets

Renliang Yuan, Jiong Zhang, Lingfeng He +1

Techniques for training artificial neural networks (ANNs) and convolutional neural networks (CNNs) using simulated dynamical electron diffraction patterns are described. The premis…

cs.CV2025

Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning

Lingfeng He, De Cheng, Di Xu +2

Continual learning (CL) aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge. With the progress of vision-language models lik…

cs.CV2024

Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID

Lingfeng He, De Cheng, Nannan Wang +1

Unsupervised visible-infrared person re-identification (USL-VI-ReID) endeavors to retrieve pedestrian images of the same identity from different modalities without annotations. Whi…

cs.CV2025

EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning

Huaijie Wang, De Cheng, Lingfeng He +4

Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired k…

cs.CV2025

Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID

De Cheng, Lingfeng He, Nannan Wang +2

Unsupervised visible-infrared person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations f…

cs.CV2023

Weakly-supervised ROI extraction method based on contrastive learning for remote sensing images

Lingfeng He, Mengze Xu, Jie Ma

ROI extraction is an active but challenging task in remote sensing because of the complicated landform, the complex boundaries and the requirement of annotations. Weakly supervised…

cs.CV2026

Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5

Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes, resulting in poor generalization on minority group…