Today in Generative Media
Fake AI candidate audio; Adobe AI video reactions; Detect deepfake video in real time
News
AI is spawning a flood of fake Trump and Harris voices. Here’s how to tell what’s real. (Washington Post)
Here’s How Adobe’s New AI Video Tool Could Upend the Ad Business (Inc.)
Video editors are already impressed by Adobe's AI video editing tool in Premiere Pro (Creative Bloq)
Startup can identify deepfake video in real time (Ars Technica)
Hungry for Energy, Amazon, Google and Microsoft Turn to Nuclear Power (New York Times)
Anyone Can Turn You Into an AI Chatbot. There’s Little You Can Do to Stop Them (Wired)
Parents sue school in Massachusetts after son punished for using AI on paper (ABC News)
I’ve seen the new AI collar that lets your dog talk, and it’s as wild as it sounds (TechRadar)
Apple researchers suggest artificial intelligence is still mostly an illusion (TechXPlore)
Adobe teases AI tools that build 3D scenes, animate text, and make distractions disappear (The Verge)
Adobe's new image rotation tool is one of the most impressive AI concepts we've seen (Creative Bloq)
Software
AI image generator shoot-out: I tested ChatGPT vs Gemini vs Meta AI to crown a winner (Tom’s Guide)
Mistral releases new AI models optimized for laptops and phones (TechCrunch)
GS^3: Efficient Relighting with Triple Gaussian Splatting (GitHub)
ComfyUI-Fluxtapoz (WIP) (GitHub) RF Inversion reimplemented in <24 hours with some super nice results (X)
Research
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats (project page)
CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos (project page) Code on GitHub
Hallo2 Long-Duration and High-Resolution Audio-driven Portrait Image Animation (project page)
Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention (project page)
Magnituder Layers for Implicit Neural Representations in 3D (arXiv)
Sample what you cant compress (arXiv)