method
active
method:nash-mtl

Nash-MTL

Gradient aggregation via Nash bargaining game.

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.

  • Aligned-MTLmethod0.738
    Independent component alignment for multi-task learning.
  • MT-Benchmethod0.680
    Benchmark used to measure general task performance of LLMs before and after SOO fine-tuning
  • DB-MTL (Dual-Balancing Multi-Task Learning)method0.678
    The proposed method combining loss-scale balancing via logarithm transformation and gradient-magnitude balancing via maximum-norm normalization.
  • Netscapeinstitute0.673
    Web company where Steenson worked as information architect in 1996.
  • MTAdammethod0.669
    Automatic balancing of multiple training loss terms.
  • Mit Media Labinstitute0.669
  • Massachusetts Institute of Technologyinstitute0.663
    Host institution for the Architecture Machine Group and Alexander's early design research.
  • Nirvāṇaconcept0.655
    The state of awakening beyond concepts; referenced as the inexpressible goal.