Member-only story
Your Daily AI Research tl;dr — 2022–08–10 🧠
Meta’s new chatbot, Video Question Answering and undesired content detection in the real world!
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 Video Question Answering with Iterative Video-Text Co-Tokenization
A novel multi-stream video encoder for video question answering that uses multiple video inputs and a new video-text iterative co-tokenization approach to answer a variety of questions related to videos.
Link to the paper: https://arxiv.org/pdf/2208.00934.pdf
2️⃣ A Holistic Approach to Undesired Content Detection in the Real World
A holistic approach to building a robust and useful natural language classification system for real-world content moderation.
“Our moderation system is trained to detect a broad set of categories of undesired content, including sexual content, hateful content, violence, self-harm, and harassment. This approach…
