DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization Paper • 2608.17067 • Published Aug 17 • 22
NearID: Identity Representation Learning via Near-identity Distractors Paper • 2604.01973 • Published Apr 2 • 30
TAPS: Task Aware Proposal Distributions for Speculative Sampling Paper • 2603.27027 • Published Mar 27 • 146
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice Paper • 2601.05175 • Published Jan 8 • 38