Understand this story
InternLM has open-sourced Sage-SciPerception (Shusheng·Yuanzheng), which maps scientific encoders for molecular graphs, spectra, crystal structures, protein and nucleic acid sequences, among others, into the language model input space through a trainable projector, and trains them separately by task. On the QM9S joint spectral-structure recognition task, the project achieves Acc@1 of 49.75%; on BEACON ncRNA family classification, accuracy is 97.35%; and on JARVIS-DFT formation energy prediction, MAD/MAE is 15.03. The project provides three demos, and the projector checkpoint will be released on Hugging Face.
AI-generated from public reports
Developments
1 confirmed developments
Sage Sci Perception provides the ability to connect scientific encoders to language models
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 6
An original InternLM projectFirst-party
InternLM Open-Sources Sage-SciPerception (ShuSheng·YuanZheng): Connecting Scientific Encoders to Language Models
InternLM has open-sourced Sage-SciPerception (ShuSheng·YuanZheng), which maps scientific encoders such as molecular graphs, spectra, crystal structures, protein and nucleic acid sequences into the language model input space through a trainable projector, and trains them separately by task. On QM9S joint spectral-structure recognition, Acc@1 is 49.75%; on BEACON ncRNA family classification, accuracy is 97.35%; and on JARVIS-DFT formation energy prediction, MAD/MAE is 15.03. The project provides three demos, and the projector checkpoint will be released on Hugging Face.