The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published about 1 month ago • 170
Function2Scene: 3D Indoor Scene Layout from Functional Specifications Paper • 2605.30819 • Published May 29 • 42
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders Paper • 2605.22777 • Published May 21 • 5
Stream-T1: Test-Time Scaling for Streaming Video Generation Paper • 2605.04461 • Published May 6 • 109
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models Paper • 2604.21106 • Published Apr 27 • 10