8 papers
CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding
Zhenyu Yi, Qiang Hu, Zhenhao Li +3
Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that bu…
Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies
Zhenyu Yi, Zhiyun Song, Yusong Sun +6
Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and the limited semantic underst…
Task-free Adaptive Meta Black-box Optimization
Chao Wang, Licheng Jiao, Lingling Li +4
Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure…
PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
Henghui Ding, Chang Liu, Nikhila Ravi +33
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challen…
MASSeg : 2nd Technical Report for 4th PVUW MOSE Track
Xuqiang Cao, Linnan Zhao, Jiaxuan Zhao +3
Complex video object segmentation continues to face significant challenges in small object recognition, occlusion handling, and dynamic scene modeling. This report presents our sol…
Learning Evolution via Optimization Knowledge Adaptation
Chao Wang, Lingling Li, Licheng Jiao +3
The iterative search process of evolutionary algorithms (EAs) encapsulates optimization knowledge within historical populations and fitness evaluations. Effective utilization of th…