8 papers
NormDirection: Restoring the Missing Query Norm in Vision Linear Attention
Weikang Meng, Yadan Luo, Liangyu Huo +4
Linear attention mitigates the quadratic complexity of softmax attention but suffers from a critical loss of expressiveness. We identify two primary causes: (1) The normalization o…
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…
Off-the-shelf Vision Models Benefit Image Manipulation Localization
Zhengxuan Zhang, Keji Song, Junmin Hu +2
Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-spe…
MirrorLA: Reflecting Feature Map for Vision Linear Attention
Weikang Meng, Liangyu Huo, Yadan Luo +3
Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance…
STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs
Weikang Meng, Liangyu Huo, Yadan Luo +4
Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention.…
Bolster Hallucination Detection via Prompt-Guided Data Augmentation
Wenyun Li, Zheng Zhang, Dongmei Jiang +1
Large language models (LLMs) have garnered significant interest in AI community. Despite their impressive generation capabilities, they have been found to produce misleading or fab…