Today in Generative Media
RunwayML offers $1M grants; Andy Serkis teases AI project; AI checks & balances
News
Andy Serkis Teases New Project Featuring “AI Characters” (Deadline)
Rethinking ‘Checks and Balances’ for the A.I. Age (New York Times)
ChatGPT is changing the way we write. Here’s how – and why it’s a problem (The Conversation)
Software
NotebookLM adds audio and YouTube support, plus easier sharing of Audio Overviews (Google Keyword blog)
Llama-3.2 on WebGPU 🦙 Blazing fast inference with WebGPU and WebLLM running locally in your browser. (HuggingFace)
LivePortrait is amazing! That's exactly what I needed. I wrapped fofrAI 's model in a bit of JavaScript. (X) Demo.
gradio_webrtc: Stream images in realtime with WebRTC (GitHub)
ComfyUI Mini: A mobile-friendly frontend to run ComfyUI workflows (GitHub)
Research
PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis (ECCV 2024, arXiv)
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction (project page)
Next-Token Prediction is All You Need (project page)
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness (project page)