AI Wiki — Knowledge Base

How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function

arXiv:2604.17581v1 Announce Type: new Abstract: How much data is enough to make a scientific discovery? As biomedical datasets scale to millions of samples and AI models grow in capacity, progress inc

researcharxiv-cs-lg

21 Apr 2026

Search: “scaling-laws”

From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law Regimes

Scaling Laws for Mixture Pretraining Under Data Constraints

X-MoD: Practical Scaling Laws for Sparse-Depth Routing Beyond Mixture-of-Depths

Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection

Multi-Stream Attention Residuals

How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine

Smooth Scaling Laws Hide Stepwise Token Learning

TuringViT: Making SOTA Vision Transformers Accessible to All

Machine Learning for Electron-Scale Turbulence Modeling in W7-X

OmniEEG-Bench: A Standardized Evaluation Benchmark for EEG Foundation Models

Inferring the Size of Large Language Models From Popular Text Memorization

On the Optimizer Dependence of Neural Scaling Laws

Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference

TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation

Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World

The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws

Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation

Knowledge Transfer Scaling Laws for 3D Medical Imaging

Is there 'Secret Sauce'' in Large Language Model Development?

Prescriptive Scaling Laws for Data Constrained Training

CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model

How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function

Is More Data Worth the Cost? Dataset Scaling Laws in a Tiny Attention-Only Decoder