This work introduces Trion-1, the first native, unified, multimodal diffusion language model (dLLM) for proteins, which unifies six core capabilities: folding, inverse folding, sequence understanding, structure understanding, sequence design, and structure design, while retaining the native language capabilities of gen...
Tian-Yu Lu, Kai-Cheng Yang, Jiang-Tao Feng et al.· 0 citations
This study conducts extensive evaluations across a wide range of settings and demonstrates that ProFiT is a plug-and-play tokenizer adaptable to diverse downstream tasks and further reveals the significant potential of the flow matching tokenizer paradigm.
Zhe Zhang, Yi-Kai Zhang, Jiang-Tao Feng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.