TEDBench/miae-b-ft

TEDBench — Fine-tuned from pretrained MiAE (structure only)

Variant: miae_b  |  Parameters: 102M  |  Layers: 12  |  Hidden dim: 768  |  Attn heads: 12

This MiAEClassifier was initialised from a pretrained MiAE and fine-tuned on TEDBench for fold classification. This model was presented in the paper Protein Fold Classification at Scale: Benchmarking and Pretraining.

Part of the TEDBench benchmark for protein fold classification (ICML 2026). MiAE is an SE(3)-invariant masked autoencoder that masks up to 90% of backbone frames and reconstructs the full structure with a lightweight decoder.

Official Code: https://github.com/BorgwardtLab/TEDBench

Architecture sizes

Variant	Params	Layers	Hidden dim	Attn heads
miae_s	29 M	6	512	8
miae_b	102 M	12	768	12
miae_l	339 M	24	1 024	16

Append +model.use_seq_input=true to miae_b for the +seq variant.

Usage

Load from the HuggingFace Hub

from tedbench.utils.io import load_from_hf

model = load_from_hf("TEDBench/miae-b-ft")
model.eval()

From a Lightning checkpoint

from tedbench.model import MiAEClassifier

model = MiAEClassifier.load_from_checkpoint("model.ckpt", weights_only=False)
model.eval()

Citation

@inproceedings{chen2026tedbench,
  title={Protein Fold Classification at Scale: Benchmarking and Pretraining},
  author={Chen, Dexiong house, Andrei Manolache, Mathias Niepert, Karsten Borgwardt},
  booktitle={Proceedings of the 43rd International Conference on Machine Learning},
  year={2026}
}