Weijian Mai
2 papers · Latest:
Computer Vision
Elastic Attention Cores for Scalable Vision Transformers
VECA introduces elastic core-periphery attention for Vision Transformers, achieving linear-time complexity and competitive performance with learned core tokens.
2605.12491
Machine LearningMeta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
A meta-learning method allows training-free, cross-subject fMRI brain decoding by inferring individual neural patterns in-context, eliminating fine-tuning.
2604.08537
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.