5 papers · 1 filter
Efficient Adversarial Training via Criticality-Aware Fine-Tuning
Wenyun Li, Zheng Zhang, Dongmei Jiang +2
Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalab…
DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection
Guiping Cao, Xiangyuan Lan, Wenjian Huang +3
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g.,…
Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval
Yushuai Sun, Zikun Zhou, Dongmei Jiang +4
Asymmetric retrieval is a typical scenario in real-world retrieval systems, where compatible models of varying capacities are deployed on platforms with different resource configur…
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
Zhehan Kan, Ce Zhang, Zihan Liao +7
Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing sig…
EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment
Yifei Xing, Xiangyuan Lan, Ruiping Wang +4
Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, cu…