3 papers
cs.CV2025
SynPo: Boosting Training-Free Few-Shot Medical Segmentation via High-Quality Negative Prompts
Yufei Liu, Haoke Xiao, Jiaxing Chai +4
The advent of Large Vision Models (LVMs) offers new opportunities for few-shot medical image segmentation. However, existing training-free methods based on LVMs fail to effectively…
cs.CV2025
YH-MINER: Multimodal Intelligent System for Natural Ecological Reef Metric Extraction
Mingzhuang Wang, Yvyang Li, Xiyang Zhang +9
Coral reefs, crucial for sustaining marine biodiversity and ecological processes (e.g., nutrient cycling, habitat provision), face escalating threats, underscoring the need for eff…
cs.CV2025
Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT
Dongyang Liu, Shicheng Li, Yutong Liu +16
Recent advancements have established Diffusion Transformers (DiTs) as a dominant framework in generative modeling. Building on this success, Lumina-Next achieves exceptional perfor…