pith. sign in

Galore: Memory-efficient llm training by gradient low-rank projection

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

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

representative citing papers

Model Merging: Foundations and Algorithms

cs.LG · 2026-05-02 · unverdicted · novelty 6.0

New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.

citing papers explorer

Showing 2 of 2 citing papers.

  • ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning cs.LG · 2026-05-20 · conditional · none · ref 16

    ChunkFT enables full-parameter fine-tuning of Llama 3-8B on one 24 GB GPU and Llama 3-70B on two 80 GB GPUs by streaming gradients over dynamically activated sub-tensors.

  • Model Merging: Foundations and Algorithms cs.LG · 2026-05-02 · unverdicted · none · ref 202

    New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.