arXiv Machine Learning June 8, 2026 By Zhiwei Xu, Shihao Wu, Hanseul Cho, Wei Hu, Yixin Wang

Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 2

When Data Is Scarce: Scaling Sparse Language Models with Repeated Training

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.

By Boqian Wu, Qiao Xiao, Patrik Okanovic, Tomasz Sternal, Maurice van Keulen, Mykola Pechenizkiy, Elena Mocanu, Torsten Hoefler, Decebal Constantin Mocanu

llms efficiency

arXiv AI

Jun 16

Data Augmentations for Data-Constrained Language Model 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.

By Michael K. Chen, Xikun Zhang, Zhen Wang

llms

arXiv AI

Jul 29

Bridging Compute- and Data-Optimal Pretraining

arXiv:2607. 25271v1 Announce Type: cross Abstract: Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data.

By Tian Qin, Kimia Hamidieh, David Alvarez-Melis

Hugging Face Trending Papers

Jul 28

Bridging Compute- and Data-Optimal Pretraining

Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data. We propose Compute-Data (CD) scaling laws, a unified framework that bridges compute-optimal scaling, where data scales freely with compute, and data-optimal scaling, where the corpus is fixed while compute can grow without bound.

arXiv AI

Jul 17

In-Place Tokenizer Expansion for Pre-trained LLMs

arXiv:2607. 15232v1 Announce Type: cross Abstract: A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time.

By Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera, Simon S. Lee, Paul Pak, Aditya Tadimeti, Tim Seyde, Maxime Labonne, Alexander Amini, Mathias Lechner

llms rag nlp

arXiv Machine Learning

Jul 15

Inference-Time Machine Unlearning via Gated Activation Redirection

arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.

By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u

llms efficiency safety

Related stories

When Data Is Scarce: Scaling Sparse Language Models with Repeated Training

Data Augmentations for Data-Constrained Language Model Pretraining

Bridging Compute- and Data-Optimal Pretraining

Bridging Compute- and Data-Optimal Pretraining

In-Place Tokenizer Expansion for Pre-trained LLMs

Inference-Time Machine Unlearning via Gated Activation Redirection