6 papers
Addressable Memory for Video World Models
Xindi Wu, Sven Elflein, James Lucas +5
We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames.…
Motion Attribution for Video Generation
Xindi Wu, Despoina Paschalidou, Jun Gao +5
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a m…
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
NVIDIA, :, Aarti Basant +32
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving pol…
Variance Reduction for Expectations with Diffusion Teachers
Jesse Bettencourt, Xindi Wu, Matan Atzmon +2
Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pi…
Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond
Jessie Richter-Powell, Antonio Torralba, Jonathan Lorraine
We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation…
Multi-student Diffusion Distillation for Better One-step Generators
Yanke Song, Jonathan Lorraine, Weili Nie +2
Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep inference procedure. To overcome this, diffusion distillation techniques produce student…