Apple Proposes DynaMiCS for Constrained Multi-Domain LLM Fine-Tuning

Jul 10, 2026

Apple ML Research has introduced DynaMiCS, a dynamic mixture optimizer that frames multi-domain fine-tuning of large language models as a constrained optimization problem. DynaMiCS uses short probing runs to estimate a slope matrix and enforces performance constraints on domains such as safety and instruction following, aiming to improve target domain performance while preserving capabilities in constrained domains.

Why it matters: This approach addresses the challenge of enhancing specific skills in large language models without sacrificing general knowledge or safety, which is crucial for reliable deployment.

Full story at: Apple Machine Learning Research ↗