JD
Jiahua Dong
cs.CVcs.LGcs.AIcs.CLcs.ROeess.IVAlgorithmsDeep LearningArabidopsisArtificial Intelligence
On Valency
published · living versionsW_fju6e3df·v1 · currentpublished
Task Relevance-Driven Prompt Expansion for Federated Continual Learning
with Wenqi Liang, Yang Cong, Yichen Li, Hongyuan Yu +4
1 version
W_y729mjn9·v1published
Preprints & journals
68 papers in the corpus · 2019–2026Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization.42258692 · Dong, Jiahua, Liang, Wenqi, Li, Hongliu et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):12211-12228
Never-Ending Behavior-Cloning Agent for Robotic Manipulation.42678871 · Liang, Wenqi, Sun, Gan, He, Yao et al.2026 · 0 citationsIEEE transactions on neural networks and learning systems. 2026;PP
ReasonWalker: Reasoning Iterative Vision-and-Language Navigation With Implicit Instructions.42599864 · Wang, Xudong, Liu, Baichen, Dong, Jiahua et al.2026 · 0 citationsIEEE transactions on cybernetics. 2026;PP
Learning From Each Other: Generalized Federated Incremental Semantic Segmentation.41678480 · Dong, Jiahua, Liang, Wenqi, Cong, Yang et al.2026 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(6):6929-6947
BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks2605.15766v2 · Loka Li, Duzhen Zhang, Xingbo Du et al.2026 · 0 citationsarXiv
From System 1 to System 2: A Survey of Reasoning Large Language Models.41289126 · Zhang, Duzhen, Li, Zhong-Zhi, Zhang, Ming-Liang et al.2026 · 49 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(3):3335-3354
SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning2601.04699v1 · Zebin Han, Xudong Wang, Baichen Liu et al.2026 · 1 citationarXiv
IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting.41525545 · Fu, Hao, Zhao, Hanbin, Dong, Jiahua et al.2026 · 3 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;35:717-731
CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation.41817988 · Liu, Baichen, Lyu, Qi, Wang, Xudong et al.2026 · 0 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;35:2816-2829
Bring Your Dreams to Life: Continual Text-to-Video Customization2512.05802v2 · Jiahua Dong, Xudong Wang, Wenqi Liang et al.2025 · 0 citationsarXiv
Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding2512.00805v2 · Pengfei Hu, Meng Cao, Yingyao Wang et al.2025 · 0 citationsarXiv
PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model2511.01571v2 · Wenqi Liang, Gan Sun, Yao He et al.2025 · 0 citationsarXiv
Accurate Tracking of Arabidopsis Root Cortex Cell Nuclei in 3D Time-Lapse Microscopy Images Based on Genetic Algorithm.41052158 · Song, Yu, Goh, Tatsuaki, Li, Yinhao et al.2025 · 0 citationsIEEE transactions on computational biology and bioinformatics. 2025;22(6):3260-3272
Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion2510.13198v1 · Rongtao Xu, Jinzhou Lin, Jialei Zhou et al.2025 · 0 citationsarXiv
SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis2510.06694v1 · Jipeng Lyu, Jiahua Dong, Yu-Xiong Wang2025 · 0 citationsarXiv
Deep self-cleansing for medical image segmentation with noisy labels.40983942 · Dong, Jiahua, Zhang, Yue, Wang, Qiuli et al.2025 · 1 citationMedical physics. 2025;52(10):e70007
Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images2509.15758v1 · Yue Zhang, Jiahua Dong, Chengtao Peng et al.2025 · 0 citationsarXiv
MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph2508.12393v3 · Duzhen Zhang, Zixiao Wang, Zhong-Zhi Li et al.2025 · 2 citationsarXiv
Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation2508.08612v1 · Jiahua Dong, Hui Yin, Wenqi Liang et al.2025 · 0 citationsarXiv
Exploring Stability-Plasticity Trade-offs for Continual Named Entity Recognition2508.03259v1 · Duzhen Zhang, Chenxing Li, Jiahua Dong et al.2025 · 0 citationsarXiv
Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment2508.00945v1 · Yifan Wang, Hongfeng Ai, Quangao Liu et al.2025 · 0 citationsarXiv
Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning2507.10348v3 · Yichen Li, Xiuying Wang, Wenchao Xu et al.2025 · 3 citationsarXiv
Enhancing Multimodal Continual Instruction Tuning with BranchLoRA2506.02041v1 · Duzhen Zhang, Yong Ren, Zhong-Zhi Li et al.2025 · 2 citationsarXiv
Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models2503.18923v2 · Meng Cao, Pengfei Hu, Yingyao Wang et al.2025 · 2 citationsarXiv
Resource-Constrained Federated Continual Learning: What Does Matter?2501.08737v2 · Yichen Li, Yuying Wang, Jiahua Dong et al.2025 · 2 citationsarXiv
MuseumMaker: Continual Style Customization Without Catastrophic Forgetting.40238617 · Liu, Chenxi, Sun, Gan, Liang, Wenqi et al.2025 · 12 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;34:2499-2512
SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images2412.05274v1 · Jiahua Dong, Tong Wu, Rui Qian et al.2024 · 0 citationsarXiv
Federated Incremental Named Entity Recognition2411.11623v3 · Duzhen Zhang, Yahan Yu, Chenxing Li et al.2024 · 1 citationarXiv
Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models2411.02564v2 · Meng Cao, Yuyang Liu, Yingfei Liu et al.2024 · 0 citationsarXiv
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?2410.17594v1 · Jiahua Dong, Wenqi Liang, Hongliu Li et al.2024 · 6 citationsarXiv
Open-Ended Online Learning for Autonomous Visual Perception.37027689 · Yu, Haibin, Cong, Yang, Sun, Gan et al.2024 · 8 citationsIEEE transactions on neural networks and learning systems. 2024;35(8):10178-10198
PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer2407.03813v1 · Qian Feng, Hanbin Zhao, Chao Zhang et al.2024 · 0 citationsarXiv
Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging2406.00449v1 · Jiahua Dong, Hui Yin, Hongliu Li et al.2024 · 1 citationarXiv
Rehearsal-free Federated Domain-incremental Learning2405.13900v2 · Rui Sun, Haoran Duan, Jiahua Dong et al.2024 · 3 citationsarXiv
Federated Learning with New Knowledge: Fundamentals, Advances, and Futures2402.02268v1 · Lixu Wang, Yang Zhao, Jiahua Dong et al.2024 · 5 citationsarXiv
MM-LLMs: Recent Advances in MultiModal Large Language Models2401.13601v5 · Duzhen Zhang, Yahan Yu, Jiahua Dong et al.2024 · 259 citationsarXiv
Federated Continual Novel Class Learning2312.13500v1 · Lixu Wang, Chenxi Liu, Junfeng Guo et al.2023 · 1 citationarXiv
Continual Named Entity Recognition without Catastrophic Forgetting2310.14541v1 · Duzhen Zhang, Wei Cong, Jiahua Dong et al.2023 · 21 citationsarXiv
InOR-Net: Incremental 3-D Object Recognition Network for Point Cloud Representation.37027587 · Dong, Jiahua, Cong, Yang, Sun, Gan et al.2023 · 12 citationsIEEE transactions on neural networks and learning systems. 2023;34(10):6955-6967
Tailored multi-organ segmentation with model adaptation and ensemble.37725849 · Dong, Jiahua, Cheng, Guohua, Zhang, Yue et al.2024 · 1 citationComputers in biology and medicine. 2023;166:107467
Create Your World: Lifelong Text-to-Image Diffusion2309.04430v1 · Gan Sun, Wenqi Liang, Jiahua Dong et al.2023 · 51 citationsarXiv
I3DOD: Towards Incremental 3D Object Detection via Prompting2308.12512v1 · Wenqi Liang, Gan Sun, Chenxi Liu et al.2023 · 2 citationsarXiv
Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition2308.08793v1 · Duzhen Zhang, Hongliu Li, Wei Cong et al.2023 · 20 citationsarXiv
Heterogeneous Forgetting Compensation for Class-Incremental Learning2308.03374v2 · Jiahua Dong, Wenqi Liang, Yang Cong et al.2023 · 24 citationsarXiv
Gradient-Semantic Compensation for Incremental Semantic Segmentation2307.10822v1 · Wei Cong, Yang Cong, Jiahua Dong et al.2023 · 28 citationsarXiv
Self-paced Weight Consolidation for Continual Learning2307.10845v1 · Wei Cong, Yang Cong, Gan Sun et al.2023 · 30 citationsarXiv
Towards AI-Architecture Liberty: A Comprehensive Survey on Design and Generation of Virtual Architecture by Deep Learning2305.00510v4 · Anqi Wang, Jiahua Dong, Lik-Hang Lee et al.2023 · 2 citationsarXiv
Federated Incremental Semantic Segmentation2304.04620v1 · Jiahua Dong, Duzhen Zhang, Yang Cong et al.2023 · 59 citationsarXiv
Xformer: Hybrid X-Shaped Transformer for Image Denoising2303.06440v2 · Jiale Zhang, Yulun Zhang, Jinjin Gu et al.2023 · 12 citationsarXiv
No One Left Behind: Real-World Federated Class-Incremental Learning2302.00903v3 · Jiahua Dong, Hongliu Li, Yang Cong et al.2023 · 78 citationsarXiv
Career total: 101 works. 68 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.