pinned
Running
1
GlotWeb
🕸
Indexing the presence of low-resource languages on the web.
NLP, Representation Learning, Machine Translation
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
Indexing the presence of low-resource languages on the web.
Identify the language of a sentence with confidence scores
Identify languages in code-switched text
Multilingual LLM Leaderboard via Cross-Lingual Alignment