BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization
Paper
•
2505.24689
•
Published
•
1
Sander Land
sanderland
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+
Languages and Cultures
new activity
3 months ago
Skywork/Skywork-Reward-V2-Llama-3.1-8B-40M:Expected output
liked
a dataset
5 months ago
BAAI/Infinity-Instruct
Organizations
upvoted
2
papers
6 months ago
upvoted
3
papers
8 months ago
Understanding Likelihood Over-optimisation in Direct Alignment Algorithms
Paper
•
2410.11677
•
Published
•
1
Command A: An Enterprise-Ready Large Language Model
Paper
•
2504.00698
•
Published
•
29
Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models
Paper
•
2405.05417
•
Published
•
1