Qishuai Wen

ShuaiLupin

5

·

AI & ML interests

None yet

Recent Activity

authored a paper 9 days ago

Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights

authored a paper 9 days ago

Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective

authored a paper 9 days ago

Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few

View all activity

Organizations

None yet

Papers 3

arxiv:2602.01219

arxiv:2509.16875

arxiv:2411.03033

models 0

None public yet

datasets 0

None public yet