method
active
method:mtadam

MTAdam

Automatic balancing of multiple training loss terms.

Neighborhood — ranked by edge-count

Artifacts (1)

artifact

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • MT-Benchmethod0.745
    Benchmark used to measure general task performance of LLMs before and after SOO fine-tuning
  • The primary contribution of the paper: a bidirectional causal method that learns rotation matrices for each model to uncover and compare causally relevant latent subspaces across neural networks.
  • n-dimensional association model can express binding mechanisms for multimethods by letting values range over methods of arity n and applying appropriate α and β transformations.
  • Aligned-MTLmethod0.696
    Independent component alignment for multi-task learning.
  • GradNormframework0.695
    Gradient balancing method learning task weights; DB-MTL improves on its approach
  • Enables agents to self-manage internal context window by providing a clean_memory tool that selectively preserves important information when approaching token limits.
  • nondeterminismconcept0.688
    Inherent in Linda because an in statement chooses one matching tuple arbitrarily; essential for many parallel patterns.
  • Medium-term memoryconcept0.678
    Vascular clamp's function: holding specific predictions stable over timescales longer than working memory.