iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Bloomberg Delays India's Sovereign Bond Index Inclusion as Market Reforms Need Further Testing Gold loans jump 93.8% y-o-y, fuel bank credit growth in Q1FY27 Snapchat joins YouTube, LinkedIn and Substack in fight against 'AI slop' Amazon speeds last-mile delivery, expands robotics fleet past 1 million Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Bloomberg Delays India's Sovereign Bond Index Inclusion as Market Reforms Need Further Testing Gold loans jump 93.8% y-o-y, fuel bank credit growth in Q1FY27 Snapchat joins YouTube, LinkedIn and Substack in fight against 'AI slop' Amazon speeds last-mile delivery, expands robotics fleet past 1 million
Home ›› Topics ›› pretraining

Topic

pretraining

7 stories
New Research Shows Pretraining Data Composition Can Engineer Neural Scaling Laws for Particle Physics Technology
Artificial Intelligence #scaling laws#pretraining

New Research Shows Pretraining Data Composition Can Engineer Neural Scaling Laws for Particle Physics

A new arXiv paper demonstrates that neural scaling laws in particle physics can be engineered by adjusting pretraining data composition. The study shows that including more diverse and task-aligned synthetic data can shift scaling behavior to require more data rather than larger models, offering insights for efficient AI training.

Jul 8, 2026 1 source
IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources Technology
Artificial Intelligence #natural language processing#persian nlp

IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources

Researchers present IHUBERT, a monolingual Persian language model pretrained on a 45GB curated subset of the Sepahr-Danesh collection using a multi-stage pipeline that includes vector-database-based semantic deduplication and domain-balanced pretraining. IHUBERT achieves top scores on extractive QA benchmarks PQuAD and ParsiNLU-RC, and best results on FarsTail NLI, while remaining competitive on NER and topic classification.

Jun 20, 2026 1 source
Researchers Identify Shrinkage Bias in LLM FP4 Pretraining, Propose UFP4 Recipe for Stability Technology
Artificial Intelligence #llm#pretraining

Researchers Identify Shrinkage Bias in LLM FP4 Pretraining, Propose UFP4 Recipe for Stability

A new study from researchers on arXiv identifies 'Shrinkage Bias' in E2M1-based FP4 pretraining for large language models, a systematic error that accumulates across layers. The proposed UFP4 recipe, using uniform grids like E1M2/INT4, demonstrates lower BF16-relative loss degradation on models up to 124B parameters, urging hardware support for uniform 4-bit formats.

Jun 20, 2026 1 source
Spokes Optimizes Diverse Pretraining Data Selection for LLMs, Boosting Performance Technology
Artificial Intelligence #spokes#diverse pretraining

Spokes Optimizes Diverse Pretraining Data Selection for LLMs, Boosting Performance

Researchers introduce Spokes, a method that directly optimizes diversity in pretraining data selection for large language models. Using a probabilistic framework based on the G-Vendi score and exponentiated gradient descent, Spokes achieves significantly more diverse subsets and improves downstream performance by up to 1.5 points over random sampling.

Jun 16, 2026 1 source
EyeMVP AI Model Enhances Retinal Screening by Learning OCT Insights from Fundus Photos Technology
Artificial Intelligence #artificial intelligence#computer vision

EyeMVP AI Model Enhances Retinal Screening by Learning OCT Insights from Fundus Photos

Researchers developed EyeMVP, a cross-modal retinal foundation model that enriches color fundus photography (CFP) with depth-resolved information from optical coherence tomography (OCT). Pretrained on 674,893 paired images from 112,642 patients across eight Chinese hospitals, EyeMVP outperforms leading models on 16 downstream tasks including macular edema detection (AUROC 0.948 vs 0.852) and myopic macular schisis (0.825).

Jun 16, 2026 1 source
Data Augmentations Offer Path to Efficient Language Model Pretraining Under Data Constraints Technology
Artificial Intelligence #data augmentation#language model

Data Augmentations Offer Path to Efficient Language Model Pretraining Under Data Constraints

As AI labs face a data ceiling where compute capacity outpaces new high-quality text, researchers propose data augmentations to enable productive multi-epoch training on fixed corpora. Three categories—token-level noise, sequence permutations, and target offset prediction—are shown to delay overfitting and lower validation loss compared to standard autoregressive pretraining. Random token replacement achieved the best minimum loss among individual methods, with combined augmentations further improving results.

Jun 16, 2026 1 source
X-Tokenizer: Semantic Action Tokenizer Boosts Robot Control by 13.5% Over FAST Technology
Artificial Intelligence #x-tokenizer#multimodal

X-Tokenizer: Semantic Action Tokenizer Boosts Robot Control by 13.5% Over FAST

Researchers propose X-Tokenizer, a new action tokenizer that treats tokenization as semantic interface learning rather than mere compression. Using a lightweight encoder-Semantic Residual Quantization (SRQ)-decoder architecture, it improves multimodal grounding by 13.5% and long-horizon task performance by 8.25 points over existing methods like FAST.

Jun 16, 2026 1 source