arxiv
PublishedJuly 10, 2026 at 4:00 AM
▲bullish
Efficient Long-Horizon Learning for Learned Optimization
Publisher summary· verbatim
arXiv:2607.06772v2 Announce Type: replace Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent work has greatly advanced the architectural design and inductive bi
Models mentioned
03Related
05- arxivJul 31NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus
- arxivJun 2How Much Orthogonalization Does Muon Need?
- arxivMay 1Making Logic a First-Class Citizen in Generative ML for Networking
- arxivApr 20Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
- arxivApr 10Information as Structural Alignment: A Dynamical Theory of Continual Learning
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivAre Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents49marxivSciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks49marxivBeyond NL2Code: A Structured Survey of Multimodal Code Intelligence49marxivWho Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs49mThe Bubble Brief
WEEKLYRead optimization insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗