Today in Generative Media
NYT's AI reporting tool; "Open source" includes data; Music & voice partnerships
News
How The New York Times is using generative AI as a reporting tool (Ars Technica)
Open-source AI must reveal its training data, per new OSI definition (The Verge)
Universal Music partners with AI company building an ‘ethical’ music generator (The Verge)
SAG-AFTRA signs agreement with AI-powered voice company Ethovox (Game Developer)
A mysterious new image generation model has appeared (TechCrunch)
The AI boom may unleash a global surge in electronic waste (Washington Post)
Margaret Atwood’s verdict on AI poetry is in — and it’s not good (TechCrunch)
Software
Research
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats (NeurIPS 2024 project page)
FreeGaussian: Guidance-free Controllable 3D Gaussian Splats with Flow Derivatives (project page)
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision (project page)
Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Gaussian Splatting (arXiv)
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion (arXiv)