Recipe adapts pretrained autoregressive image models to any token order
On LlamaGen and RAR, the method beat MaskGIT inpainting FID 6.21 to 10.44 at 13-33% extra compute.
6 stories, newest first · one card per story
On LlamaGen and RAR, the method beat MaskGIT inpainting FID 6.21 to 10.44 at 13-33% extra compute.
On MIMIC-IV, a block size of 8 evaluates about 1.43 times faster, while linear probes nearly match autoregressive models.
A diffusion planner drafts K parallel reasoning paths; a large autoregressive model selects one and writes the answer.
ModAR autoregressively denoises multiple future modalities (point tracks, DINO features, depth) before predicting actions, beating prior world-action models at all data scales.
PhysStream enables mid-generation interactive control of physics-grounded video via structured scene memory and velocity-increment signals, reducing motion distribution distance 33%.
Researchers propose Mask Forcing, a dual-noise masking rollout that mitigates mode collapse in autoregressive video diffusion distillation.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views