activity
20242026
collaborators

5 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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.…

cs.CV2025

PolaFormer: Polarity-aware Linear Attention for Vision Transformers

Weikang Meng, Yadan Luo, Xin Li +2

Linear attention has emerged as a promising alternative to softmax-based attention, leveraging kernelized feature maps to reduce complexity from quadratic to linear in sequence len…

cs.CV2024

SC3D: Label-Efficient Outdoor 3D Object Detection via Single Click Annotation

Qiming Xia, Hongwei Lin, Wei Ye +4

LiDAR-based outdoor 3D object detection has received widespread attention. However, training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box anno…