pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

baseline 1

citation-polarity summary

fields

cs.LG 1 cs.MM 1

years

2026 2

verdicts

UNVERDICTED 2

roles

baseline 1

polarities

baseline 1

clear filters

representative citing papers

GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond

cs.LG · 2026-06-02 · unverdicted · novelty 7.0

GFFMERGE formulates GNN force field merging as a convex embedding-alignment problem with an analytical solution, recovering near joint-training performance on MD17, MD22, LiPS20 and other benchmarks while delivering 5-27x speedups.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond cs.LG · 2026-06-02 · unverdicted · none · ref 52

    GFFMERGE formulates GNN force field merging as a convex embedding-alignment problem with an analytical solution, recovering near joint-training performance on MD17, MD22, LiPS20 and other benchmarks while delivering 5-27x speedups.