Solvaformer: an SE(3)-equivariant graph transformer for small molecule solubility prediction

Accurate prediction of small molecule solubility using material-sparing approaches is critical for accelerating synthesis and process optimization, yet experimental measurement is costly and many learning approaches either depend on quantumderived descriptors or offer limited interpretability. We introduce Solvaformer, a geometry-aware graph transformer that models solutions as multiple molecules with independent SE(3) symmetries. The architecture combines intramolecular SE(3)-equivariant attention with intermolecular scalar attention, enabling cross-molecular communication without imposing spurious relative geometry. We train Solvaformer in a multi-task setting to predict both solubility (log S) and solvation free energy, using an alternating-batch regimen that trains on quantum-mechanical data (CombiSolv-QM) and on experimental measurements (BigSolDB 2.0). Solvaformer attains the strongest overall performance among the learned models and approaches a DFT-assisted gradient-boosting baseline, while outperforming an EquiformerV2 ablation and sequence-based alternatives. In addition, token-level attention produces chemically coherent attributions: case studies recover known intra- vs. inter-molecular hydrogen-bonding patterns that govern solubility differences in positional isomers. Taken together, Solvaformer provides an accurate, scalable, and interpretable approach to solution-phase property prediction by uniting geometric inductive bias with a mixed dataset training strategy on complementary computational and experimental data.

Gait Cycle Reconstruction and Human Identification from Occluded Sequences

Gait-based person identification from videos captured at surveillance sites using Computer Vision-based techniques is quite challenging since these walking sequences are usually corrupted with occlusion, and a complete cycle of gait is not always available. In this work, we propose an effective neural network-based model to reconstruct the occluded frames in an input sequence before carrying out gait recognition. Specifically, we employ LSTM networks to predict an embedding for each occluded frame both from the forward and the backward directions, and next fuse the predictions from the two LSTMs by employing a network of residual blocks and convolutional layers. While the LSTMs are trained to minimize the mean-squared loss, the fusion network is trained to optimize the pixel-wise cross-entropy loss between the ground-truth and the reconstructed samples. Evaluation of our approach has been done using synthetically occluded sequences generated from the OU-ISIR LP and CASIA-B data and real-occluded sequences present in the TUM-IITKGP data. The effectiveness of the proposed reconstruction model has been verified through the Dice score and gait-based recognition accuracy using some popular gait recognition methods. Comparative study with existing occlusion handling methods in gait recognition highlights the superiority of our proposed occlusion reconstruction approach over the others.