Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
5
The first holistic framework for a Tajik electronic dictionary could revolutionize NLP applications in low-resource languages.
Forget full fine-tuning: QLoRA on 7B models can match the perplexity of fully fine-tuned smaller models for low-resource languages, while slashing the parameter count by 40x.
Learn to build and evaluate your own NLP pipeline, from tokenization to RLHF, using open-weight models and reproducible research practices.