This weekend in Generative Media

GenAI cultural pollution; OpenAI's voice model, artist-in-residence, & Hollywood tour

• A.I.-Generated Garbage Is Polluting Our Culture (New York Times)

• OpenAI Unveils A.I. Technology That Recreates Human Voices (New York Times) Navigating the Challenges and Opportunities of Synthetic Voices (OpenAI blog)

• A conversation with OpenAI’s first artist in residence (MIT Technology Review)

• Sam Altman is trying to convince Hollywood that Sora won't destroy the movie business (Business Insider) OpenAI shows off Sora AI video generator to Hollywood execs (Ars Technica)

• Despite the Panic, Generative AI Won’t Be on the Big Screen Any Time Soon (IndieWire)

• Adobe’s new AI tool can turn anyone into an infographics wiz (FastCompany)

• How SAG-AFTRA union views AI and gaming negotiations | Sarah Elmaleh interview (VentureBeat)

• How to Resist the Temptation of AI When Writing (Wired)

• VideoSwap: Customized Video Subject Swapping with Interactive Semantic

  Point Correspondence (CVPR 2024, project page)

• TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models (CVPR 2024, project page)

• Learning Inclusion Matching for Animation Paint Bucket Colorization (project page)

• CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians (project page)

• Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions (project page)

• MonoHair: High-Fidelity Hair Modeling from a Monocular Video (project page)

• My Photoshop is more fun than yours😉 (X)