compute-optimal

Tag

Cards List
#compute-optimal

Scaling Native Multimodal Pre-Training From Scratch

Hugging Face Daily Papers · 2026-07-24 Cached

This paper investigates the scaling properties of native multimodal pre-training, deriving compute-optimal model sizes and token counts under a fixed budget, and revealing distinct scaling behaviors for language and multimodal objectives.

0 favorites 0 likes
#compute-optimal

How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size

arXiv cs.LG · 2026-07-03 Cached

Proposes a three-term scaling law that decouples model size, training steps, and batch size, enabling robust fitting with fewer runs and deriving scaling laws for suboptimal batch sizes.

0 favorites 0 likes
#compute-optimal

@lilianweng: A super long overdue (3+ years?) post on scaling laws. Compute is expensive. Scaling laws are a way to help us reason a…

X AI KOLs Timeline · 2026-06-25 Cached

Lilian Weng's blog post provides a comprehensive overview of scaling laws in deep learning, covering their derivation, compute-optimal allocation, and the debate between Kaplan et al. and Chinchilla.

0 favorites 0 likes
#compute-optimal

A Bitter Lesson for Data Filtering (1 minute read)

TLDR AI · 2026-05-21 Cached

This paper investigates data filtering for large model pretraining and finds that in the high-compute, data-scarce regime, filtering may not be necessary and can even be detrimental; sufficiently trained large models benefit from nominally low-quality data.

1 favorites 1 likes
#compute-optimal

Compute Optimal Tokenization (2 minute read)

TLDR AI · 2026-05-13 Cached

This paper systematically derives compression-aware neural scaling laws by training nearly 1,300 models, demonstrating that the widely used heuristic of 20 tokens per parameter is an artifact of specific tokenizers. The authors propose a tokenizer-agnostic scaling law based on bytes, offering a new framework for compute-efficient training across diverse languages and modalities.

0 favorites 0 likes
#compute-optimal

Prescriptive Scaling Laws for Data Constrained Training

Hugging Face Daily Papers · 2026-05-02 Cached

A modified scaling law accounting for data repetition effects provides compute-optimal training strategies for data-constrained scenarios, showing that beyond a point further repetition is counterproductive and compute is better spent on model capacity.

0 favorites 0 likes
← Back to home

Submit Feedback