Today in Generative Media
Natasha Lyonne faces AI backlash; Meta plans AI risk assessment; AI Content 2025
News and Opinion
Natasha Lyonne addresses backlash to her AI "hybrid" movie (AV Club)
Meta plans to replace humans with AI to assess privacy and societal risks (NPR)
AI in Content Creation 2025: A global look at how creators, marketers, educators, and teams are building with AI today (WonderCraft)
A.I. Killed the Math Brain (New York Times)
The future of engineering belongs to those who build with AI, not without it (VentureBeat)
How AI coding agents could destroy open source software (ZDNet)
Inside an AI Story Lab, Part III: Sound, Deep Time and Deep Imagination in AI Cinema (Elettra Fiumi on Substack)
The recent history of AI in 32 otters (Ethan Mollick on Substack)
Software
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment (HuggingFace)
Real-time markerless motion capture (CyanPuppets)
UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes (GitHub)
We found the secret to use multiple images with FLUX.1 Kontext: Use our Image Stitch node! (X)
Kontext Chat, Powered by FLUX.1 Kontext on Replicate: Chat with images to edit them. (Replicate)
Research
Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing (project page)
MAGREF: Masked Guidance for Any-Reference Video Generation (project page)
LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering (project page)
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities (project page)
WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions (project page)
PS4PRO: Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization (arXiv)