Member-only story
Your Daily AI Research tl;dr — 2022–09–13 🧠
MIT researchers have made DALL-E more creative, Contact-rich Grasp Synthesis for Multi-fingered Hands and Temporal Action Composition for 3D Humans…
Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.
1️⃣ TEACH: Temporal Action Composition for 3D Humans
Given a series of natural language descriptions, TEACH generates 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions.
Link to the paper: https://arxiv.org/pdf/2209.04066.pdf
Code: https://github.com/athn-nik/teach
2️⃣ Grasp’D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands
Grasp’D: an approach for grasp synthesis with a differentiable contact simulation from both known models as well as visual inputs.