This weekend in Generative Media

Imran Khan's AI victory speech; Machines always helped writers; AI menaces news biz

• Imran Khan’s ‘Victory Speech’ From Jail Shows A.I.’s Peril and Promise (New York Times)

• ChatGPT is nothing new. Machines have helped us write for centuries. (Washington Post)

• Opinion: The real wolf menacing the news business? AI. (Washington Post)

• Stability, Midjourney, Runway hit back in AI art lawsuit (VentureBeat) AI Companies Take Hit as Judge Says Artists Have “Public Interest” In Pursuing Lawsuits (Hollywood Reporter)

• Meet the Pranksters Behind Goody-2, the World’s ‘Most Responsible’ AI Chatbot (Wired)

• Watermarking in the sand (Harvard Kempner Institute blog)

• 3DGS Appears in Usher Music Video (RadianceFields.com)

• You can now generate AI art on your TV with a Raspberry Pi (XDA Developers)

• Seven reasons why the world should say No to Sam Altman (Gary Marcus on Substack)

• SplashPro: Create songs with AI.

• EscherNet: A Generative Model for Scalable View Synthesis (project page)

• AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation (project page)

• Collaborative Control for Geometry-Conditioned PBR Image Generation (project page)

• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization (project page)

• Denoising Diffusion via Image-Based Rendering (project page)

• ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation (project page)

• BUD-E: Enhancing AI voice assistants’ conversational quality, naturalness, and empathy. (project page)

• Keyframer: Empowering Animation Design using Large Language Models (arXiv)

• Pollution of the information ecosystem is not something to be proud of. (X)

• I did not write this book. Nor did Frank Alkyer, editor of DownBeat. (X)

• Midjourney V6 Understands Colors like never before! (X)

• Video Upscaling to 8k / 60 FPS rolling out soon. (X)