Ye et al. find that language model loss on each domain follows an exponential function of training mixture proportions. By nesting data mixing laws with scaling laws for steps and model size, small-scale experiments can predict and optimize mixtures for large models, achieving 48% training efficiency gains.
Xie et al. propose DoReMi, which trains a 280M proxy model using Group DRO to find optimal domain mixture weights, then uses those weights to train an 8B model 2.6x faster with 6.5% better downstream accuracy.
Muennighoff et al. train 400+ models to study how data repetition affects scaling. They propose a data-constrained scaling law with exponential decay for repeated tokens, finding that up to 4 epochs have negligible impact on loss, returns diminish around 16 epochs, and code augmentation provides a 2x effective data boost.
Shen et al. empirically analyze how different domain combinations and deduplication strategies in the SlimPajama dataset affect 1.3B model performance. Global deduplication across sources outperforms local deduplication, and increasing domain diversity consistently improves average accuracy, with findings transferring to 7B scale.
Raffel et al. introduce T5, a unified text-to-text framework for NLP transfer learning. Through systematic ablation of architectures, pre-training objectives, datasets, and multi-task mixing strategies, they identify best practices and scale to 11B parameters, achieving state-of-the-art results across multiple benchmarks.
A transformer architecture that applies a recurrent cell over blocks of tokens, achieving linear complexity in sequence length while outperforming Transformer-XL baselines on PG19, arXiv, and GitHub datasets.
Proposes Ewald message passing, a Fourier-space scheme inspired by Ewald summation that captures long-range interactions in molecular graphs. The method is architecture-agnostic and improves energy MAEs by 10% on OC20 and 16% on OE62 across four baseline GNN models.
Lagrangian Neural Networks (LNNs) use neural networks to parameterize arbitrary Lagrangians, enabling energy-conserving learned dynamics without canonical coordinates. Unlike Hamiltonian approaches, LNNs handle relativistic systems and extend to graphs via Lagrangian Graph Networks.
Liquid-S4 extends the S4 framework by incorporating a linearized liquid time-constant formulation that introduces input-dependent state transitions. This yields an additional convolutional kernel capturing input correlations, improving generalization across long-range sequence tasks.
RWKV is a novel sequence model that achieves transformer-level performance while maintaining linear time and constant memory complexity during inference, scaled up to 14 billion parameters.
InChI (International Chemical Identifier) is an open standard from IUPAC that represents molecular structures as hierarchical, layered strings optimized for database interoperability, unique identification, and web search via its hashed InChIKey.
An 831M-parameter encoder-decoder model that jointly encodes image, OCR text, and layout information through a two-stage training strategy, achieving state-of-the-art multimodal Markush structure recognition while remaining competitive on standard molecular structure recognition.