pdf

N/A

# link_1me38ryxil4.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=true - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20231121045447Z - Creator=LaTeX with hyperref - ModDate=D:20231121045447Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Producer=pdfTeX-1.40.25 - Trapped=False ## Contents ### Page 1 EXPLOITING CODE SYMMETRIES FOR LEARNING PRO-GRAM SEMANTICSAnonymous authorsPaper under double-blind reviewABSTRACTLarge Language Models (LLMs) hold

saved by

• Dhilan Shah

related reading

• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Contrastive Code Representation Learningparasj.github.io
• Composer2.pdfcursor.com
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
• Transformer Circuits Threadtransformer-circuits.pub
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
• Naturally Occurring Equivariance in Neural Networksdistill.pub
• Verifying your browser | OpenReviewopenreview.net
• 10. Equivariant Neural Networks — deep learning for molecules & materialsdmol.pub
• Overleaf Examplearxiv.org
• Set Transformer: A Framework for Attention-basedPermutation-Invariant Neural Networksarxiv.org