The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture Paper • 2607.17146 • Published 17 days ago • 5
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models Paper • 2605.21573 • Published May 20 • 111
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation Paper • 2605.11739 • Published May 13 • 61
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 238
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems Paper • 2605.04018 • Published May 5 • 41