Lukas Edman

leukas's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 4 papers 5 days ago

Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs

Paper • 2510.20475 • Published 10 days ago • 1

EXECUTE: A Multilingual Benchmark for LLM Token Understanding

Paper • 2505.17784 • Published May 23

Are BabyLMs Second Language Learners?

Paper • 2410.21254 • Published Oct 28, 2024

Subword-Delimited Downsampling for Better Character-Level Translation

Paper • 2212.01304 • Published Dec 2, 2022

authored a paper 10 months ago

CUTE: Measuring LLMs' Understanding of Their Tokens

Paper • 2409.15452 • Published Sep 23, 2024 • 1

authored a paper over 2 years ago

Are Character-level Translations Worth the Wait? Comparing Character- and Subword-level Models for Machine Translation

Paper • 2302.14220 • Published Feb 28, 2023