BAGEL: Bootstrapping Agents by Guiding Exploration with Language
Murty, Shikhar, Manning, Christopher, Shaw, Peter, Joshi, Mandar, Lee, Kenton
Year of Publication 12.03.2024
Year of Publication 12.03.2024
Get full text
Journal Article
Pushdown Layers: Encoding Recursive Structure in Transformer Language Models
Murty, Shikhar, Sharma, Pratyusha, Andreas, Jacob, Manning, Christopher D
Year of Publication 29.10.2023
Year of Publication 29.10.2023
Get full text
Journal Article
Grokking of Hierarchical Structure in Vanilla Transformers
Murty, Shikhar, Sharma, Pratyusha, Andreas, Jacob, Manning, Christopher D
Year of Publication 30.05.2023
Year of Publication 30.05.2023
Get full text
Journal Article
MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
Kallini, Julie, Murty, Shikhar, Manning, Christopher D, Potts, Christopher, Csordás, Róbert
Year of Publication 28.10.2024
Year of Publication 28.10.2024
Get full text
Journal Article
Fixing Model Bugs with Natural Language Patches
Murty, Shikhar, Manning, Christopher D, Lundberg, Scott, Ribeiro, Marco Tulio
Year of Publication 07.11.2022
Year of Publication 07.11.2022
Get full text
Journal Article
Characterizing Intrinsic Compositionality in Transformers with Tree Projections
Murty, Shikhar, Sharma, Pratyusha, Andreas, Jacob, Manning, Christopher D
Year of Publication 02.11.2022
Year of Publication 02.11.2022
Get full text
Journal Article
BAGEL: Bootstrapping Agents by Guiding Exploration with Language
Murty, Shikhar, Manning, Christopher, Shaw, Peter, Joshi, Mandar, Lee, Kenton
Published in arXiv.org (09.06.2024)
Get full text
Published in arXiv.org (09.06.2024)
Paper
Grokking of Hierarchical Structure in Vanilla Transformers
Murty, Shikhar, Sharma, Pratyusha, Jacob, Andreas, Manning, Christopher D
Published in arXiv.org (30.05.2023)
Get full text
Published in arXiv.org (30.05.2023)
Paper
Fixing Model Bugs with Natural Language Patches
Murty, Shikhar, Manning, Christopher D, Lundberg, Scott, Ribeiro, Marco Tulio
Published in arXiv.org (20.11.2022)
Get full text
Published in arXiv.org (20.11.2022)
Paper