activity
20172026
most citedGradient Descent Maximizes the Margin of Homogeneous Neural Networks

102 citations · 280 across the 26 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching

Zeyang Zhang, Linxiang Gao, Meiqi Gu +4

Recent work has explored visual reasoning through image generation, where models solve visual-reasoning problems by directly generating solution images. Intuitively, iterative samp…