5 papers · 1 filter
Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
Jingen Qu, Lijun Li, Bo Zhang +2
Multimodal large language models (MLLMs) are rapidly evolving, presenting increasingly complex safety challenges. However, current dataset construction methods, which are risk-orie…
CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization
Yichen Yan, Ming Zhong, Qi Zhu +3
Multimodal large language models (MLLMs) rely heavily on instruction tuning to align vision and language capabilities, yet the computational cost of training on large-scale dataset…
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions
Wenxuan Wang, Yisi Zhang, Xingjian He +4
Visual grounding (VG) aims at locating the foreground entities that match the given natural language expressions. Previous datasets and methods for classic VG task mainly rely on t…
Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation
Yichen Yan, Xingjian He, Sihan Chen +2
Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous method…
Calibration & Reconstruction: Deep Integrated Language for Referring Image Segmentation
Yichen Yan, Xingjian He, Sihan Chen +1
Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-gra…