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.
A 2025 Vision-Language Model for OCSR that uses graph traversal chain-of-thought reasoning and a two-stage SFT plus GRPO training scheme to handle both printed molecules (including chemical abbreviations like Ph and Et) and hand-drawn structures, achieving strong performance on the new MolRec-Bench benchmark.
Proposes the ‘Optical Chemical Structure Understanding’ (OCSU) task to translate molecular images into multi-level descriptions (motifs, IUPAC, SMILES). Introduces the Vis-CheBI20 dataset and two paradigms: DoubleCheck (OCSR-based) and Mol-VL (OCSR-free).
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.
A comprehensive phylogenomic study dating LUCA to ~4.2 Ga and reconstructing it as a complex, anaerobic acetogen. The authors apply the cross-bracing molecular clock method alongside gene-tree-species-tree reconciliation to infer that LUCA possessed an early immune system and lived within a hydrogen-recycling ecosystem.
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.
We explore the ‘Silent Failure’ mode of LLMs in production: the limits of 99% accuracy for reliability, how confidence decays in long documents, and why standard calibration techniques struggle to fix it.
We trace the history of Page Stream Segmentation (PSS) through three eras (Heuristic, Encoder, and Decoder) and explain how privacy-preserving, localized LLMs enable true semantic processing.