Thinking Machines' Dimuon Optimizer Beats AdamW on LoRA Fine-Tuning Steps

Thinking Machines rolled out Dimuon, a LoRA-specific optimizer that beats AdamW on step count in supervised fine-tuning while leaving RL mostly unchanged.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-15 00:56 · AlphaSignal
Thinking Machines' Dimuon Optimizer Beats AdamW on LoRA Fine-Tuning Steps

More stories

OpenAI engineer arrested for planting surveillance device in office — Sky News Technology
Eight US states sue OpenAI over alleged child safety failures — The Verge AI
Anthropic reports $16.8 billion Q3 revenue ahead of planned IPO — Bloomberg AI
Meta Study: Most Small Businesses Use AI for Productivity — Meta Newsroom
Sources: Anthropic told investors that its revenue jumped to $16.8B in Q3, up from $11.5B in Q2, and that the company was profitable on an adjusted basis in Q3 (Financial Times) — Techmeme
OpenAI Agrees Not to Use Alleged Apple Trade Secrets During Lawsuit — Bloomberg AI
Google and Meta release new frontier AI models amid benchmark comparisons — Google Gemini Blog
Amazon Bedrock AgentCore enables enterprise AI agents for IT, security, and document processing — AWS Machine Learning Blog

Get the daily brief of stories like this at 6:30 every morning →