Comparing Muon, NorMuon and AdamW for Fine-tuning a Dense Retriever

Qingcheng Zeng gives Muon and NorMuon the same tuning budget as AdamW when fine-tuning a contrastively pretrained dense retriever: lower training loss, no BEIR win. Learning rate and transfer matter more than the optimizer.

Research · Machine Learning · Research · LLMs · Benchmarks

An Empirical Study of Harness Design for Coding Agents

Fan et al. ablate planning, action space, and context management in a fixed coding-agent loop across 176 SWE-Bench/Terminal-Bench settings, finding when context management, planning, and predefined tools help—and when bash-only is enough.

Research · AI Agents · AI · Research · Machine Learning

Project HydraFusion: Frontier quality via multi-model orchestration

In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated cost through multi-model orchestration.

Research · AI · LLMs · Developer Tools · Programming

Developing provably correct Rust code with Verus

Many open-source and industry software projects, including several here at Amazon, are embracing the Rust programming language, since it provides performance and flexibility similar to that of the C programming language, while its clever type system automatically prevents a variety of bugs and security vulnerabilities. The result is fast code that's more correct and secure than average.

Research · Rust · Research · Security · Programming

Semantics for 2D Rasterization

Kulkarni, Whiting, and Panchekha introduce μSkia—a Lean-mechanized formal semantics for Skia 2D graphics—and an optimizer that speeds rasterization ~18.7% on Chrome-derived Skia programs while proving replacements correct.

Research · Research · Performance · Programming · Hardware