Last-Iterate Guarantees for Online Reinforcement Learning in Structured Constrained MDPsResearchSep 29, 2026
SignFLIP: A Unified Model for Sign Language Translation and Generation via Stage-wise Alignment at ScaleResearchSep 29, 2026
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision ModelResearchSep 29, 2026