2023-3-19 arXiv roundup: GPT-4, Data deduplication, MoE optimizationsThis newsletter made possible by MosaicML. GPT-4 Technical Report This is a 98-page document, so we’re just gonna go through some highlights. First, scaling is still going strong. We haven’t saturated the log-log-linear trend yet. This holds not just for the pretraining…
2023-2-26 arXiv roundup: RLHF for diffusion, Multimodal chain of thought, Practical data poisoningThis newsletter made possible by MosaicML. Poisoning Web-Scale Training Datasets is Practical You can poison public datasets by buying domains …
1
2023-2-26 arXiv roundup: RLHF for diffusion, Multimodal chain of thought, Practical data poisoning
dblalock.substack.com
2023-1-22 arXiv roundup: Domain-specific pretraining is awesome, Removing skip connectionsThis newsletter made possible by MosaicML. Looks like we’ve got a little bit of a pre-ICML lull this week. But next week might be crazy… Learning…
1
2023-1-22 arXiv roundup: Domain-specific pretraining is awesome, Removing skip connections
dblalock.substack.com
Davis Summarizes Papers
Davis Summarizes Papers
dblalock.substack.com
Davis Summarizes Papers
I go through all the machine learning arXiv submissions each week and summarize 10 to 20 of my favorites. Free forever and read by thousands of ML researchers and practitioners.
By registering you agree to Substack's Terms of Service, our Privacy Policy, and our Information Collection Notice