4 papers
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
Xiaomin Yu, Yi Xin, Yuhui Zhang +12
Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of d…
Text-Only Data Synthesis for Vision Language Model Training
Xiaomin Yu, Wenjie Zhang, Ziyue Qiao +2
Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is costly. In contrast, text data is…
DescriptorMedSAM: Language-Image Fusion with Multi-Aspect Text Guidance for Medical Image Segmentation
Wenjie Zhang, Liming Luo, Mengnan He +2
Accurate organ segmentation is essential for clinical tasks such as radiotherapy planning and disease monitoring. Recent foundation models like MedSAM achieve strong results using…
QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
Xinyang Tong, Pengxiang Ding, Yiguo Fan +9
This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) task…