GraSP introduces a general framework for recognizing graphs in images by framing it as sequential subgraph prediction with a binary classifier. A GNN conditions a CNN via FiLM layers to predict whether a candidate graph is a subgraph of the target. Applied to OCSR on QM9, GraSP achieves 67.5% accuracy with no domain-specific modifications.

Derives the optimal rotation between two 3D point sets as the eigenvector of a 4x4 symmetric matrix built from cross-covariance sums, using unit quaternions to enforce the orthogonality constraint.

A foundational 1976 short communication presenting a direct, non-iterative method for finding the best rotation matrix between two point sets via eigendecomposition of a cross-covariance matrix.

This paper introduces Latent Diffusion Models (LDMs), which apply denoising diffusion in the latent space of pretrained autoencoders. By separating perceptual compression from generative learning and adding cross-attention conditioning, LDMs achieve FID 1.50 on Places inpainting and FID 3.60 on ImageNet class-conditional synthesis, with competitive text-to-image generation, at a fraction of the compute cost of pixel-space diffusion.

Technical report on Uni-Parser, an industrial-grade document parsing engine that uses a modular multi-expert architecture to parse scientific PDFs into structured representations. Integrates MolParser 1.5 for OCSR, achieving 88.6% accuracy on chemical structures while processing up to 20 pages per second.

Tallec and Ollivier show that requiring invariance to time transformations in recurrent models leads to gating mechanisms, recovering key LSTM components from first principles. They propose the chrono initialization for gate biases that improves learning of long-term dependencies.

Battaglia et al. argue that combinatorial generalization requires structured representations, systematically analyze the relational inductive biases in standard deep learning architectures (MLPs, CNNs, RNNs), and present the graph network as a unifying framework that generalizes and extends prior graph neural network approaches.

Tay et al. systematically compare scaling laws across ten diverse architectures (Transformers, Switch Transformers, Performers, MLP-Mixers, and others), finding that the vanilla Transformer has the best scaling coefficient and that the best-performing architecture changes across compute regions.

Fuchs et al. introduce the SE(3)-Transformer, which combines self-attention with SE(3)-equivariance for 3D point clouds and graphs. Invariant attention weights modulate equivariant value messages from tensor field networks, resolving angular filter constraints while enabling data-adaptive, anisotropic processing.

Cohen et al. introduce Spherical CNNs that achieve SO(3)-equivariance by defining cross-correlation on the sphere and rotation group, computed efficiently via generalized FFT algorithms from non-commutative harmonic analysis.

Baldi and Vershynin systematically classify the fundamental building blocks of attention (activation attention, output gating, synaptic gating) by source, target, and mechanism, then prove capacity bounds showing that gating introduces quadratic terms sparsely, gaining expressiveness without the full cost of polynomial activations.

MOSES introduces a comprehensive benchmarking platform for molecular generative models, offering standardized datasets, evaluation metrics, and baselines. By providing a unified measuring stick, it aims to resolve reproducibility challenges in chemical distribution learning.