A5101812316- Topic Modeling
- Advanced Image and Video Retrieval Techniques
- Multimodal Machine Learning Applications
- Biomedical Text Mining and Ontologies
- Image Retrieval and Classification Techniques
- Natural Language Processing Techniques
- Intelligent Tutoring Systems and Adaptive Learning
Henan University of Technology
2021
Existing Large Vision-Language Models (LVLMs) can process inputs with context lengths up to 128k visual and text tokens, yet they struggle generate coherent outputs beyond 1,000 words. We find that the primary limitation is absence of long output examples during supervised fine-tuning (SFT). To tackle this issue, we introduce LongWriter-V-22k, a SFT dataset comprising 22,158 examples, each multiple input images, an instruction, corresponding ranging from 0 10,000 Moreover, achieve maintain...
The vast pre-existing slides serve as rich and important materials to carry lecture knowledge. However, effectively leveraging students is difficult due the multi-modal nature of slide content heterogeneous teaching actions. We study problem discovering effective designs that convert a into an interactive lecture. develop Slide2Lecture, tuning-free knowledge-regulated intelligent tutoring system can (1) input structured agenda consisting set actions; (2) create manage generates responsive...
The medical information carried in electronic records has high clinical research value, and named entity recognition is the key to extracting valuable from large-scale texts. At present, most of studies on Chinese are based character vector model or word model. Owing complexity specificity text, existing methods may fail achieve good performance. In this study, we propose a method that fuses vectors. expresses texts as vectors separately them for features. proposed can effectively avoid...