AI Video Summaries on YouTube 🎥 // Generative AI for Audio 🎵 // Synthetic Dataset for Point Tracking 🕹️
Description
YouTube is experimenting with AI-generated video summaries, potentially changing the way creators structure their videos. AudioCraft, a generative AI for audio, is now available to all and could revolutionize the way we create and experience audio. PointOdyssey, a synthetic dataset and data generation framework, aims to advance the state-of-the-art in long-term fine-grained tracking algorithms. A new attack method on aligned language models demonstrates the vulnerability of even aligned models to adversarial attacks, raising important questions about preventing objectionable content.
Contact: sergi@earkind.com
Timestamps:
00:34 Introduction
01:33 YouTube uses AI to summarize videos in latest test
02:58 Open sourcing AudioCraft: Generative AI for audio made simple and available to all
04:52 Show HN: Learn a language quickly by practising speaking with AI (prettypolly.app)
05:50 Fake sponsor
07:54 PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking
09:35 Three Bricks to Consolidate Watermarks for Large Language Models
11:14 Universal and Transferable Adversarial Attacks on Aligned Language Models
13:39 Outro
United States
