Your Daily AI Research tl;dr — 2022–09–07 🧠

Aligning language models with human values, Long-range Video Retrieval and “This AI newsletter is all you need” #11!

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 In conversation with Artificial Intelligence: aligning language models with human values [DeepMind]

The paper proposes interesting answers to common questions involving an agent discussing with humans and how to align such agent with us (ethically, socially…): A few of the questions discussed are… what does it mean to align conversational agents with human norms or values? Which norms or values should they be aligned with? And how can this be accomplished?

Link to the paper: https://arxiv.org/pdf/2209.00731.pdf

2️⃣ EclipSE: Efficient Long-range Video Retrieval using Sight and Sound

An audiovisual method for long-range text-to-video retrieval (i.e. training a model to retrieve…