rlacombe/glycogen-dfm-50m

GlycoGen-DFM (50M)

Converged PyTorch checkpoint (best_model.pt, random initialization seed 0) for "GlycoGen: Glycan Structure Prediction with Crystallizing Flows" (NeurIPS 2026).

• Architecture / Objective: Discrete Flow Matching + Crystallizing Flows
• Test-set top-1 structural accuracy (n = 76,774): 92.67% ± 0.05% (K=32) / 90.19% ± 0.04% (K=1)
• Code & inference scripts: github.com/rlacombe/GlycoGen
• Project page: rlacombe.github.io/GlycoGen
• Benchmark splits: rlacombe/candycrunch-v2-benchmark

Citation

@inproceedings{lacombe2026glycogen,
  title     = {GlycoGen: Glycan Structure Prediction with Crystallizing Flows},
  author    = {Lacombe, Romain},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026}
}