Author

Xiang Xiang

Observed name: Xiang, Xiang

Institution: Huazhong University of Science and Technology

Observed institution: Huazhong University of Science and Technology

OpenAlex ID: A5094302520

Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer

2024 · Yuwen Tan, Qinhao Zhou, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 21

Overcoming Shortcut Problem in VLM for Robust Out-of-Distribution Detection

2025 · Zhuo Xu, Xiang Xiang, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 9

Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning

2024 · Qinhao Zhou, Zihan Zhang, et al. · Findings of the Association for Computational Linguistics: NAACL · 3

PDF

Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning

2024 · Zhou, Qinhao, Tan, Yuwen, et al. · arXiv (Cornell University) · 2

PDF

AerialFusion: Co-Motion-Driven Unified Registration and Fusion on Multi-modal Data Streams from Aerial View

2026 · Junhui Qiu, Xiang Xiang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

PDF

Random Amalgamation of Adapters for Flatter Loss Landscapes: Towards Class-Incremental Learning with Better Stability

2026 · Yao Deng, Xiang Xiang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

PDF

MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation

2026 · Zehang Wei, JiaXin Dai, et al. · Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)

Findings of the MAGMaR 2026 Shared Task

2026 · Alexander Martin, Dengjia Zhang, et al. · Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)

PDF

Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation

2026 · JiaXin Dai, Zehang Wei, et al. · Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)

PDF

Works count: 9

Citation count: 35

H-index: 3

I10-index: 1