compute-optimization

Tag

Cards List
#compute-optimization

@rohanpaul_ai: Google DeepMind’s new routing idea is trying to solve a great practical question. Routing is supposed to save compute, …

X AI KOLs Timeline · 2026-08-22 Cached

Google DeepMind introduces a routing method framed as a Pandora's Box problem to efficiently allocate compute by deciding when to invest in better model selection estimates, demonstrating improved performance on benchmarks like MATH, RAG, and EmbedLLM.

0 favorites 0 likes
#compute-optimization

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

Hugging Face Daily Papers · 2026-08-07 Cached

The paper introduces the Skaling law, a generalized neural scaling law that couples model capacity and data through an interaction exponent, reducing prediction error by 1.5-3x and enabling full-grid extrapolation using roughly 10x less compute.

0 favorites 0 likes
#compute-optimization

Predict before you train: Scaling Laws for particle physics foundation models

arXiv cs.AI · 2026-07-31 Cached

This paper demonstrates that scaling laws fit on small transformer models can accurately predict the loss of much larger models trained on particle physics jet data, enabling compute budgets to be translated into expected physics performance before large training runs. They release five pretrained models and the full training recipe.

0 favorites 0 likes
← Back to home

Submit Feedback