Papers by Acyr Locatelli

2 papers
Nexus: Adaptive Upcycling to Efficiently Pretrain Mixture of Experts (2025.findings-emnlp)

Copied to clipboard

Challenge: Nevertheless, training from scratch on trillions of tokens remains expensive that most users can only finetune these models.
Approach: They propose to reuse parameters of dense models for the MoE layers with a router that can integrate new experts into existing trained models without hurting performance on previous domains.
Outcome: The proposed router can integrate new experts into existing trained models without hurting the performance on previous domains.
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to train multilingual large language models for many languages at once are limited due to limited model capacity, scarce high-quality data, and compute constraints.
Approach: They propose to use a universal tokenizer to improve language plasticity and adaptability to new languages by up to 20%.
Outcome: The proposed tokenizer improves language plasticity and improves plasticity towards languages that are completely unseen in the tokenizer and pretraining, by up to 5% win rate gain.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations