The paper investigates how data repetition affects Mixture-of-Experts (MoE) language models compared to dense Transformers. Across models from 80 M to 1 B active parameters, MoEs degrade more quickly as data is repeated, with performance dropping significantly beyond 4× repetition and overtaking dense models only when strong regularization is applied. The study also identifies routing stabilization and expert specialization as key factors in MoE overfitting, and explores regularization techniques that can partially mitigate this issue.
arXiv:2606. 01155v1 Announce Type: cross Abstract: Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with limited data is not.
The paper investigates training-time data augmentation as a regularizer for autoregressive language model pretraining in data‑constrained, compute‑abundant settings. It introduces three orthogonal augmentation categories—token‑level noise, sequence permutations, and target offset prediction—and shows through systematic ablations that each category delays overfitting and reduces validation loss, with random token replacement performing best individually. Combining augmentation categories further lowers the minimum validation loss, demonstrating that such augmentations mitigate data inefficiency in autoregressive pretraining.
arXiv:2606. 16246v1 Announce Type: cross Abstract: As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, language model pretraining is shifting toward a data-constrained, compute-abundant regime that demands productive multi-epoch training on fixed corpora.
arXiv:2606. 06888v1 Announce Type: new Abstract: Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over the corpus.
arXiv:2608. 14071v1 Announce Type: new Abstract: As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio (\(\mathrm{TPP}\)).
arXiv:2606. 10338v1 Announce Type: cross Abstract: Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored.
arXiv:2606. 24998v1 Announce Type: new Abstract: Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition.
arXiv:2506. 14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets.
arXiv:2609.08690v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models expand model capacity without a proportional increase in training compute, but increasing sparsity makes reliable hyp...
arXiv:2602. 19938v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets.
The paper demonstrates that layer dropout, also known as stochastic depth, can be effectively used in state‑of‑the‑art large language model (LLM) training. By optimizing the layer distribution, schedule, and optimizer settings, the authors show that layer dropout can reduce training loss while saving up to 25 % of training FLOPs. Additionally, layer dropout enables post‑training optimizations such as early exit and self‑speculative decoding, achieving up to 1.5× inference speedup with negligible accuracy loss across models ranging from 271 M to 8.2 B parameters and datasets up to 160 B tokens.
arXiv:2604.23036v2 Announce Type: replace-cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layer...