Problem: Why It's Hard to Unify Understanding and Generation in One Representation There have been many attempts to merge image understanding and image generation into a…
Introduction A game world built by a video generation model alone stores off-screen state nowhere. Every time a corridor you have already passed through is redrawn, it…
StepAudio 3 Gen: Unifying Speech, Song, Music, and Sound Effects with a Single Discrete Autoregressive (RVQ) Model TL;DR StepAudio 3 Gen, released by StepFun, is a fully…
Programmable World Model — Embedding "Executable State" into Generative Worlds One-Line Summary (TL;DR) Video world models are producing increasingly realistic…
Marigold V2: Reviving an Image-Editing Diffusion Transformer (DiT) as a Monocular Depth Estimator TL;DR This study fine-tunes an image-editing diffusion transformer…
Linear Attention Rewritten with a Kalman Filter: Kalman Delta Networks TL;DR The fixed-size recurrent memory update of linear attention is reinterpreted as a…