Metraipolis › archive › dc_bdd08ccac85d
Trion-1: Unifying Language, Protein Sequence, and Structure with Diffusion Language Models — arXiv:2610.31215
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31215
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T20:53:20.714Z
- SHA-256 of the archived text
bf710c5afd9104b8c500ac5bcdfc63d6bddec982e330fc81051b34ff7f36d857- Stable URL of this page
https://metraipolis.com/documento/dc_bdd08ccac85d
How to cite
Trion-1: Unifying Language, Protein Sequence, and Structure with Diffusion Language Models — arXiv:2610.31215 — arXiv (en), https://arxiv.org/abs/2610.31215 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bdd08ccac85d (Metraipolis archive dc_bdd08ccac85d, sha256 bf710c5afd9104b8c500ac5bcdfc63d6bddec982e330fc81051b34ff7f36d857)
BibTeX
@misc{dcbdd08ccac85d,
title = {Trion-1: Unifying Language, Protein Sequence, and Structure with Diffusion Language Models — arXiv:2610.31215},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31215},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bdd08ccac85d; sha256 bf710c5afd9104b8c500ac5bcdfc63d6bddec982e330fc81051b34ff7f36d857},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31215. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We envision a general-purpose protein foundation model as a unified, interactive model of sequence, structure, and function, capable of understanding, generation, and cross-modal translation while retaining the instruction-following and reasoning capabilities of modern LLMs. Toward this vision, we introduce Trion-1, the first native, unified, multimodal diffusion language model (dLLM) for proteins. Trion-1 is built on two key design choices: (1) a unified discrete token space that jointly represents sequence, structure, and natural language; (2) a dLLM backbone that replaces strict left-to-right factorization with bidirectional or semi-bidirectional token interactions, enabling global residue communication and long-range contact modeling that are naturally suited to structure modeling. This formulation unifies six core capabilities: folding, inverse folding, sequence understanding, structure understanding, sequence design, and structure design, while retaining the native language capabilities of general-purpose LLMs. On established benchmarks, Trion-1 achieves broadly competitive performance. In folding, Trion-1 achieves a TM-score above 0.8 with a single sample under strict homology control, matching or exceeding the existing tri-modal model using 200 samples. For sequence understanding, Trion-1 performs on par with top-tier LLMs such as Claude Opus 4.7 (62.37%). These results support well-aligned sequence-structure-language representations and strong cross-modal generative capabilities. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.31215 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T20:47:56.917Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).