11 papers
Computer-Aided Design Generation by Cascaded Discrete Diffusion Model
Honghu Pan, Xiaoling Luo, Yongyong Chen +2
Recent deep learning approaches seek to automate CAD creation by representing a model as a sequence of discrete commands and parameters, and then generating them using autoregressi…
Maximizing Incremental Information Entropy for Contrastive Learning
Jiansong Zhang, Zhuoqin Yang, Xu Wu +3
Contrastive learning has achieved remarkable success in self-supervised representation learning, often guided by information-theoretic objectives such as mutual information maximiz…
Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networks
Zhuoqin Yang, Jiansong Zhang, Xiaoling Luo +3
Attention mechanisms have become a key module in modern vision backbones due to their ability to model long-range dependencies. However, their quadratic complexity in sequence leng…
MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement
Meidan Ding, Jipeng Zhang, Wenxuan Wang +4
Medical Vision-Language Models (MedVLMs) excel at perception tasks but struggle with complex clinical reasoning required in real-world scenarios. While reinforcement learning (RL)…
Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models
Shaonan Liu, Guo Yu, Xiaoling Luo +4
Medical Multimodal Large Language Models (Med-MLLMs) require egocentric clinical intent understanding for real-world deployment, yet existing benchmarks fail to evaluate this criti…
Text Condition Embedded Regression Network for Automated Dental Abutment Design
Mianjie Zheng, Xinquan Yang, Xuguang Li +5
The abutment is an important part of artificial dental implants, whose design process is time-consuming and labor-intensive. Long-term use of inappropriate dental implant abutments…