Skip to main content
Search

# Machine Translation

4 related articles

Subscribe to updates
  1. bioRxiv

    REXzyme translates a chemical reaction into an enzyme sequence, and its formate dehydrogenase design C20 reaches 2.5 times wild-type activity

    Enzyme engineering has relied on directed evolution, which screens thousands of variants even though fewer than 5% of single mutations are beneficial. REXzyme recasts enzyme design as translation: an encoder reads a reaction written in SMILES and a decoder generates an amino acid sequence token by token, after training on about 21 million reaction-enzyme pairs. Steered toward the reverse reaction of formate dehydrogenase, the reduction of CO2 to formate, all 20 designs generated after family-specific fine-tuning and reinforcement-learning alignment expressed as soluble proteins and showed activity, and design C20 reached a specific activity of 80.8 mU/mg, 2.5 times that of wild-type CtFDH.

  2. PFN opens the weights of PLaMo 3 Translate: a 0.8B model runs 53 languages offline

    Preferred Networks released PLaMo 3 Translate, a translation-specialized LLM suite originally built for its own PLaMo Translate service, as open weights on Hugging Face in four sizes (0.8B, 2B, 8B, 31B), runnable entirely offline on smartphones, laptops or internal corporate servers across 53 languages including English and Japanese. Under the PLaMo Community License, individuals and enterprises with annual revenue of 1 billion yen or less in their most recent fiscal year can download and use the models free for commercial and non-commercial purposes; larger organizations need a commercial license. PFN says its comparative evaluations put even the smallest 0.8B version ahead of comparable translation-specific LLMs such as Google's TranslateGemma and Tencent's Hy-MT2.

  3. PLaMo 3 Translate releases four weight sizes: the 0.8B model beats translation-specific models more than 30 times larger on Japanese-English and Japanese-multilingual pairs

    Preferred Networks has released weights for PLaMo 3 Translate, a translation-specific model, at 0.8B, 2B, 8B and 31B on Hugging Face, along with FP8, W4A16, NVFP4, GGUF and MLX formats for quantized and local inference. The smallest 0.8B model outperforms existing translation-specific models more than 30 times larger on Japanese-English and Japanese-to-multilingual translation, while the 2B model surpasses all existing translation-specific models on English-to-multilingual translation. Training uses two-stage supervised fine-tuning plus DPO, with smaller models distilled from the 31B teacher.

  4. PFN opens the weights of its translation-focused LLM PLaMo 3 Translate, letting the 0.8B model translate 53 languages on an offline phone

    PFN released PLaMo 3 Translate, the translation-focused large language model behind its PLaMo translation service, as open-weight models in four sizes, 0.8B, 2B, 8B and 31B, which can be embedded in phones, laptops or in-house servers to translate among 53 languages including Japanese and English without a network connection. By PFN's own evaluation, the smallest model scores above Google's TranslateGemma and Tencent's Hy-MT2 on translation quality, and companies and individuals with revenue or sales of 1 billion yen or less in the latest fiscal year may use it commercially for free under the PLaMo Community License.

You’re all caught up