Get started
Author

Weijia Li

Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More
2025 · Zichen Wen, Yifeng Gao, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 23
Haze-Aware Attention Network for Single-Image Dehazing
2024 · Lihan Tong, Yun Liu, et al. · Applied Sciences · 22
Where am I? Cross-View Geo-localization with Natural Language Descriptions
2025 · Junyan Ye, Honglin Lin, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 17
PDF
Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration
2025 · Zilong Huang, Jun He, 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
PDF
Identification of a novel splice variant isoform of interferon regulatory factor 10, IRF10, in orange spotted grouper Epinephelus coioides
2019 · B. Huang, W.X. Li, et al. · Fish & Shellfish Immunology · 6
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
2025 · Zichen Wen, Shaobo Wang, et al. · neural information processing systems · 4
PDF
Transferable image synthesis for remote sensing semantic segmentation via joint reference-semantic fusion
2025 · Runmin Dong, Shuai Yuan, et al. · Information Fusion · 3
Parallel Cross Strip Attention Network for Single Image Dehazing
2024 · Lihan Tong, Yun Liu, et al. · International Conference on Computing, Networks and Internet of Things (CNIOT) · 2
PDF
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
2026 · Junyan Ye, Leqi Zhu, et al. · Lecture notes in computer science · 1
PDF
Integrating Satellite and Street-View Images for Urban Sidewalk Extraction
2025 · Yi Lin, Jinhua Yu, et al. · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · 1
VesselTrack: Multi-object tracking of maritime vessels
2024 · Qingxia Yang, Erkang Chen, et al. · International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR) · 1
PDF
NanoTrack: An Enhanced MOT Method by Recycling Low-score Detections from Light-weight Object Detector
2024 · Weijia Li, Liyuan Chen, et al. · Asia Conference on Computer Vision, Image Processing and Pattern Recognition (CVIPPR) · 1
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
2025 · Liu, Xuyang, Wen, Zichen, et al. · arXiv (Cornell University)
PDF
LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection
2025 · Li, Weijia, Chu, Guanglei, et al. · arXiv (Cornell University)
PDF
Hybrid Modeling Digital Twin for Natural Gas Station Systems of Long-Distance Pipelines
2024 · Weijia Li, Jing Gong, et al.
PDF
Works count: 15
Citation count: 90
H-index: 5
I10-index: 3
Year
Topic
Type