GitHub

FlowWM stochastic world modeling via flow matching in DINOv3 feature space, with the FuturePerception (Waymo) benchmark.

FlowWM stochastic world modeling via flow matching in DINOv3 feature space, with the FuturePerception (Waymo) benchmark. - ...

NVIDIA’s New AI Model Could Make ChatGPT-Style Responses Much Faster

Nvidia introduces Diffusion Nemotron, a 60-billion parameter two-tower AI model that uses parallel block processing to speed up text generation.
C&EN

Fe–Al–Si Thermoelectric (FAST) Materials and Modules: Diffusion Couple and Machine-Learning-Assisted Materials Development

State Key Laboratory of Structural Chemistry, Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou 350002, P. R. China Article Views are the COUNTER-compliant ...
GitHub

Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving

Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined ...