arxiv.org/pdf/2505.24832

N/A

# link_o8rzn6oo0z.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=John X. Morris; Chawin Sitawarin; Chuan Guo; Narine Kokhlikyan; G. Edward Suh; Alexander M. Rush; Kamalika Chaudhuri; Saeed Mahloujifar - Creator=arXiv GenPDF (tex2pdf:) - Custom.DOI=https://doi.org/10.48550/arXiv.2505.24832 - Custom.License=http://creativecommons.org/licenses/by/4.0/ - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Custom.arX

saved by

• Dhruv Gautam
• Emil Ryd

related reading

• Understanding Memorization via Loss Curvaturegoodfire.ai
• Rethinking LLM Memorization – Machine Learning Blog | ML@CMU | Carnegie Mellon Universityblog.ml.cmu.edu
• [2406.10209] Be like a Goldfish, Don’t Memorize! Mitigating Memorization in Generative LLMsar5iv.labs.arxiv.org
• Why We Need Continual Learning | Andreessen Horowitza16z.com
• [2309.10668] Language Modeling Is Compressionarxiv.org
• The Little Book of Deep Learningfleuret.org
• Transformer Math 101 | EleutherAI Blogblog.eleuther.ai
• [2501.00663] Titans: Learning to Memorize at Test Timearxiv.org
• [2605.15156] MeMo: Memory as a Modelarxiv.org
• The Continual Learning Problemjessylin.com
• Memory makes computation universal, remember?thinks.lol
• Zipfian grokking | Jasper Gilleyjagilley.github.io