GutenOCR is a family of vision-language models designed to serve as a ‘grounded OCR front-end’, providing high-quality text transcription and explicit geometric grounding.
We systematically ablate core mechanisms of Transformers and RNNs, finding that attention-augmented Recurrent Highway Networks outperform standard Transformers on forecasting high-dimensional chaotic systems.
A differentiable point-set alignment library implementing N-dimensional Kabsch, Horn quaternion, and Umeyama scaling algorithms with per-point weights, batch dimensions, and custom autograd across NumPy, PyTorch, JAX, TensorFlow, and MLX.
MolGen pre-trains on 100M+ SELFIES molecules, introduces domain-agnostic prefix tuning for cross-domain transfer, and applies a chemical feedback paradigm to reduce molecular hallucinations.
The Molecular Transformer applies the Transformer architecture to forward reaction prediction, treating it as SMILES-to-SMILES machine translation. It achieves 90.4% top-1 accuracy on USPTO_MIT, outperforms quantum-chemistry baselines on regioselectivity, and provides calibrated uncertainty scores (0.89 AUC-ROC) for ranking synthesis pathways.
Presents a concise SVD-based algorithm for finding the optimal rotation and translation between two 3D point sets, with analysis of the degenerate reflection case that Umeyama later corrected.
This paper benchmarks 24 machine and deep learning methods on activity cliff compounds (structurally similar molecules with large potency differences) across 30 macromolecular targets. Traditional ML with molecular fingerprints consistently outperforms graph neural networks and SMILES-based transformers on these challenging cases, especially in low-data regimes.
The matrix-based companion to Horn’s 1987 quaternion method, deriving the optimal rotation as the orthonormal factor in the polar decomposition of the cross-covariance matrix via eigendecomposition of a 3x3 symmetric matrix.
MoLFormer is a transformer encoder with linear attention and rotary positional embeddings, pretrained via masked language modeling on 1.1 billion molecules from PubChem and ZINC. MoLFormer-XL outperforms GNN baselines on most MoleculeNet classification and regression tasks, and attention analysis reveals that the model learns interatomic spatial relationships directly from SMILES strings.
SELFormer is a transformer-based chemical language model that uses SELFIES instead of SMILES as input. Pretrained on 2M ChEMBL compounds via masked language modeling, it achieves strong classification performance on MoleculeNet tasks, outperforming ChemBERTa-2 by ~12% on average across BACE, BBBP, and HIV.
Corrects a flaw in prior SVD-based alignment methods (Arun et al., Horn et al.) that could produce reflections instead of rotations under noisy data, and provides a complete closed-form solution for similarity transformations in arbitrary dimensions.
AdaptMol combines an end-to-end graph reconstruction model with unsupervised domain adaptation via class-conditional MMD on bond features and SMILES-validated self-training. Achieves 82.6% accuracy on hand-drawn molecules (10.7 points above prior best) while maintaining state-of-the-art results on four literature benchmarks, using only 4,080 real hand-drawn images for adaptation.