openreview.net · 10,581 words · saved by 1 readers
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
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
- Lean Software Scaling Laws · Gwern.netgwern.net
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
- [2112.02969] Jigsaw: Large Language Models meet Program Synthesisarxiv.org
- Naturally Occurring Equivariance in Neural Networksdistill.pub
- Verifying your browser | OpenReviewopenreview.net
- 10. Equivariant Neural Networks — deep learning for molecules & materialsdmol.pub
- Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com