Show notes
Google DeepMind's new AI tool that generates video soundtracks by combining text prompts with visual content.Challenges of building large training AI clusters, including power, network topology, and reliability.How large language models acquire factual knowledge during pretraining and their probabilistic reasoning capabilities.LLARVA's vision-action instruction tuning that enhances robot learning.Contact:Â Â [email protected]Timestamps:01:47Â Google DeepMindâs new AI tool uses video pixels and text prompts to generate soundtracks03:31Â 100,000 H100 Clusters: Power, Network Topology, Ethernet vs InfiniBand, Reliability, Failures, Checkpointing05:22Â Large language model data pipelines and Common Crawl (WARC/WAT/WET)08:20Â How Do Large Language Models Acquire Factual Knowledge During Pretraining?10:01Â What Are the Odds? Language Models Are Capable of Probabilistic Reasoning11:22Â LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning

