1.3k citations
- Tsinghua UniversityCN130 papers
- Chinese University of Hong KongHK81 papers
- Chinese Academy of SciencesCN71 papers
- Peking UniversityCN68 papers
- Shanghai Jiao Tong UniversityCN58 papers
- Zhejiang UniversityCN54 papers
- University of Chinese Academy of SciencesCN52 papers
- Hong Kong University of Science and TechnologyHK46 papers
- Xiamen UniversityCN37 papers
- University of Hong KongHK34 papers
- Peng Cheng LaboratoryCN31 papers
- City University of Hong KongHK30 papers
11 papers · 2 filters
CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval
Bin Kang, Bin Chen, Junjie Wang +3
Existing Visual Language Models (VLMs) suffer structural limitations where a few low contribution tokens may excessively capture global semantics, dominating the information aggreg…
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
Pengfei Jiang, Hanjun Li, Linglan Zhao +4
In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference…
UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
Jinke Li, Jiarui Yu, Chenxing Wei +5
Unlike bitmap images, scalable vector graphics (SVG) maintain quality when scaled, frequently employed in computer vision and artistic design in the representation of SVG code. In…
Regularizing Subspace Redundancy of Low-Rank Adaptation
Yue Zhu, Haiwen Diao, Shang Gao +8
Low-Rank Adaptation (LoRA) and its variants have delivered strong capability in Parameter-Efficient Transfer Learning (PETL) by minimizing trainable parameters and benefiting from…
TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency
Minye Shao, Xingyu Miao, Haoran Duan +7
3D medical image generation is essential for data augmentation and patient privacy, calling for reliable and efficient models suited for clinical practice. However, current methods…
Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes
Zhaoyang Wei, Bowen Jiang, Xumeng Han +6
While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes unde…