5 papers
MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion
Haofeng Huang, Yifei Han, Long Zhang +3
Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF wi…
Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answering
Lingwen Deng, Yifei Han, Shijie Li +2
Parameter-Preserving Knowledge Editing (PPKE) enables updating models with new information without retraining or parameter adjustment. Recent PPKE approaches used knowledge graphs…
Context-Aware Pseudo-Label Scoring for Zero-Shot Video Summarization
Yuanli Wu, Long Zhang, Yue Du +1
We propose a rubric-guided, pseudo-labeled, and prompt-driven zero-shot video summarization framework that bridges large language models with structured semantic reasoning. A small…
CPCLDETECTOR: Knowledge Enhancement and Alignment Selection for Chinese Patronizing and Condescending Language Detection
Jiaxun Yang, Yifei Han, Long Zhang +5
Chinese Patronizing and Condescending Language (CPCL) is an implicitly discriminatory toxic speech targeting vulnerable groups on Chinese video platforms. The existing dataset lack…
TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning
Yu Chen, Yifei Han, Long Zhang +2
Fine-tuning large pre-trained models for downstream tasks has become a fundamental approach in natural language processing. Fully fine-tuning all model parameters is computationall…