6 papers
InsightVQA: High-Dimensional Emotion-Cognitive Visual Question Answering Benchmark
Shiyu Wang, Ziyu Liu, Chaoyi Yu +6
Visual emotion understanding requires models not only to recognize emotional states, but also to why they arise and perform higher-level cognitive reasoning. However, existing benc…
TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation
Wenbiao Tao, Xinyuan Li, Yunshi Lan +1
Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses. However, traditional RAG methods rely on fragme…
ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perception
Huanzhen Wang, Ziheng Zhou, Jiaqi Song +4
Dynamic facial expression recognition in the wild remains challenging due to data scarcity and long-tail distributions, which hinder models from effectively learning the temporal d…
RIDE: Difficulty Evolving Perturbation with Item Response Theory for Mathematical Reasoning
Xinyuan Li, Murong Xu, Wenbiao Tao +4
Large language models (LLMs) achieve high performance on mathematical reasoning, but these results can be inflated by training data leakage or superficial pattern matching rather t…
Unsupervised Text Style Transfer for Controllable Intensity
Shuhuan Gu, Wenbiao Tao, Xinchen Ma +4
Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between…
ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry
Qinwen Chen, Wenbiao Tao, Zhiwei Zhu +5
Community Question Answering (CQA) platforms can be deemed as important knowledge bases in community, but effectively leveraging historical interactions and domain knowledge in rea…