·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems4h◆Good Benchmarks4h◆On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage4h◆How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks4h◆PM-Bench: Evaluating Prospective Memory in LLM Agents4h◆Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions4h◆Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models4h◆FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation4h◆Burst Spiking Neural Networks4h◆Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design4h◆Removable Defects: The Economics and Limits of Deliberate Deficiency4h◆Sparse Inter-Layer Dependencies of Transformer FFN Neurons4h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs4h◆HPC-Enabled Video-based Coastal Wave Parameter Estimation Using V-JEPA and Deep Spatiotemporal Learning4h◆Sparse Autoencoders for Interpretable Out-of-Distribution Detection4h◆OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning4h◆Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities4h◆Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty4h◆Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques4h◆UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies4h◆Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems4h◆Good Benchmarks4h◆On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage4h◆How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks4h◆PM-Bench: Evaluating Prospective Memory in LLM Agents4h◆Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions4h◆Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models4h◆FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation4h◆Burst Spiking Neural Networks4h◆Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design4h◆Removable Defects: The Economics and Limits of Deliberate Deficiency4h◆Sparse Inter-Layer Dependencies of Transformer FFN Neurons4h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs4h◆HPC-Enabled Video-based Coastal Wave Parameter Estimation Using V-JEPA and Deep Spatiotemporal Learning4h◆Sparse Autoencoders for Interpretable Out-of-Distribution Detection4h◆OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning4h◆Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities4h◆Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty4h◆Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques4h◆UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies4h◆
News/MuCon: Clipped Muon Updates for LLM Training
arxiv
PublishedMay 27, 2026 at 4:00 AM

MuCon: Clipped Muon Updates for LLM Training

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.26459v1 Announce Type: new Abstract: Muon-style optimizers take a matrix-valued momentum or preconditioned update $B = U \operatorname{diag}(\sigma_1,\ldots,\sigma_r) V^\top$ and replace it with its canonical partial polar factor $\operatorname{Pol}(B) = U V^\top$. This maps every nonzero

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivFrom Words to Widgets for Controllable LLM Generation4harxivScalable Optimal Transport Algorithm for Network Alignment4harxivWhat Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learning4harxivWhen Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary4h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews