arxiv:2412.04626
Torsten Scholak
tscholak
AI & ML interests
NLP, semantic parsing, program synthesis, deep learning for code
Recent Activity
authored
a paper
4 days ago
BigDocs: An Open and Permissively-Licensed Dataset for Training
Multimodal Models on Document and Code Tasks
Organizations
Papers
3
models
8
tscholak/2jrayxos
Text2Text Generation
•
Updated
•
62
•
2
tscholak/2e826ioa
Text2Text Generation
•
Updated
•
15
•
7
tscholak/1wnr382e
Text2Text Generation
•
Updated
•
14
•
3
tscholak/1zha5ono
Text2Text Generation
•
Updated
•
24
•
4
tscholak/cxmefzzi
Text2Text Generation
•
Updated
•
190
•
30
tscholak/3vnuv1vf
Text2Text Generation
•
Updated
•
213
•
10
tscholak/t5.1.1.lm100k.base
Text2Text Generation
•
Updated
•
56
tscholak/t5.1.1.lm100k.large
Text2Text Generation
•
Updated
•
27
•
1
datasets
None public yet