Search Results for author:
Found 6 papers, 1 papers with code
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3, 000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1.
Factorized Transformer for Multi-Domain Neural Machine Translation
Multi-Domain Neural Machine Translation (NMT) aims at building a single system that performs well on a range of target domains.
Alibaba's Neural Machine Translation Systems for WMT18
We participated in 5 translation directions including English ↔ Russian, English ↔ Turkish in both directions and English → Chinese.
SYSTRAN Purely Neural MT Engines for WMT2017
This paper describes SYSTRAN's systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions.
Conception d'une solution de d\'etection d'\'ev\'enements bas\'ee sur Twitter (Design of a solution for event detection from Tweeter)
Cet article pr{\'e}sente un syst{\`e}me d{'}alertes fond{\'e} sur la masse de donn{\'e}es issues de Tweeter.
SYSTRAN's Pure Neural Machine Translation Systems
Since the first online demonstration of Neural Machine Translation (NMT) by LISA, NMT development has recently moved from laboratory to production systems as demonstrated by several entities announcing roll-out of NMT engines to replace their existing technologies.
