Tagged articles

gradient optimization

3 articles · Page 1 of 1

Feb 24, 2026 · Artificial Intelligence

Why Randomly Masking Gradients Can Outperform Adam in Large‑Scale Model Training

The article explains how randomly masking a large portion of gradient updates during large‑model training—sometimes up to 99%—can accelerate convergence and even surpass traditional optimizers like Adam, supported by recent Google research and empirical observations.

Distributed TrainingLarge Language ModelsMagma algorithm

0 likes · 3 min read

Why Randomly Masking Gradients Can Outperform Adam in Large‑Scale Model Training

HyperAI Super Neural

Oct 21, 2025 · Artificial Intelligence

BindCraft Enables Direct AlphaFold2‑Driven Intelligent Protein Binder Design (46% Success on 12 Targets)

BindCraft, an open‑source pipeline from EPFL and MIT, uses AlphaFold2 gradient back‑propagation to design protein binders without manual scaffolding, achieving an average 46.3% success rate across 12 challenging targets and offering a one‑click tutorial for rapid experimentation.

AlphaFold2BindCraftDeep Learning

0 likes · 5 min read

BindCraft Enables Direct AlphaFold2‑Driven Intelligent Protein Binder Design (46% Success on 12 Targets)

AI Frontier Lectures

Jul 31, 2025 · Artificial Intelligence

Can a 32‑Token Compressor Generate Images Without Training?

This article reviews a recent study that demonstrates how a highly compressed one‑dimensional tokenizer, using only 32 discrete tokens and gradient‑based test‑time optimization, can generate high‑quality images without training a separate generative model, and explores its methodology, findings, applications, and limitations.

1D tokenizerAI researchTiTok

0 likes · 10 min read

Can a 32‑Token Compressor Generate Images Without Training?