nvidia
7 stories
MODELSWorld Labs Tests Atlas Model On NVIDIA's Own HQ
World Labs ran its Atlas world model on Voyager, NVIDIA's headquarters, feeding it just 32 photos to see how well it could rebuild and fly through a real, familiar space.
NEWSRunway Reveals Lineup for Upcoming AI Summit
Runway has named the speakers for one of its AI Summit sessions, pulling in researchers from Nvidia, Google DeepMind, and Wayve to discuss grounding AI systems in physical reality.
NEWSNvidia's Jeffrey Kember Set for GenMedia Conference Talk
The GenMedia Conference has added Nvidia creative technologist Jeffrey Kember to its lineup, with a session focused on what's needed before generative media tools can work reliably at scale.
MODELSNvidia Breaks Down Mixture-of-Experts Model Efficiency
Nvidia published a technical explainer contrasting dense and mixture-of-experts architectures, showing how a 30-billion-parameter model can run using only 3 billion active parameters per token.
NEWSNvidia Creative Technologist Joins GenMedia Conference Lineup
Fal has added Jeffrey Kember, a Creative Technologist at Nvidia, to the speaker roster for its September GenMedia Conference in San Francisco, where he'll discuss what generative media tools still need to solve before wider adoption.
MODELSNVIDIA and USC Tackle Video Relighting Flicker
A new research effort called HorizonRelight aims to fix the visible lighting jumps that appear when diffusion models relight long videos in short chunks.
TOOLSNvidia Teases TensorRT Model Connect Tool
Nvidia has flagged a new offering called TensorRT Model Connect, pitched as a way to speed up development across both video and voice AI models, though details remain sparse.