4 papers
MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation
Zehang Wei, Jiaxin Dai, Jiamin Yan +1
While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and…
Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation
Jiaxin Dai, Zehang Wei, Jiamin Yan +1
This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR). Addressing the critical challenges of cross-li…
Hyperbolic Coarse-to-Fine Few-Shot Class-Incremental Learning
Jiaxin Dai, Xiang Xiang
In the field of machine learning, hyperbolic space demonstrates superior representation capabilities for hierarchical data compared to conventional Euclidean space. This work focus…
OpenHAIV: A Framework Towards Practical Open-World Learning
Xiang Xiang, Qinhao Zhou, Zhuo Xu +4
Substantial progress has been made in various techniques for open-world recognition. Out-of-distribution (OOD) detection methods can effectively distinguish between known and unkno…