Today in Generative Media
Time to prep for AI; Meta's nightmarish AI feed; Free speech for Character.AI chatbots
News and Opinion
If you haven’t been worrying about AI, it’s time to start preparing (Washington Post)
Meta’s AI app is a nightmarish social feed (The Verge)
Character.AI opens a back door to free speech rights for chatbots (Mashable)
Netflix debuts its generative AI-powered search tool (TechCrunch)
Google’s AI image-to-video generator launches on Honor’s new phones (The Verge)
An ex-Google AI ethicist and a UW professor want you to know AI isn't what you think it is (Business Insider)
How generative AI is playing out in the media industry (Computer Weekly)
AI Isn’t Just a Tool—It’s a Test (Psychology Today)
Bringing 3D shoppable products online with generative AI (Google Research blog)
Software
Google AI for game developers (Google Developers blog)
llama.cpp supports multimodal input (GitHub)
Research
SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation (project page)
MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation (project page)
Introducing Continuous Thought Machines (project page)
High Dynamic Range Novel View Synthesis with Single Exposure (arXiv)
Rethinking Score Distilling Sampling for 3D Editing and Generation (arXiv)
Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control (arXiv)
Geometry-Aware Texture Generation for 3D Head Modeling with Artist-driven Control (arXiv)
Real-Time Person Image Synthesis Using a Flow Matching Model (arXiv)