pith. sign in

Learning rate scaling across LoRA ranks and transfer to full finetuning

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

Learning When to Adapt

cs.LG · 2026-05-18 · conditional · novelty 6.0

DISeL augments standard LoRA with per-input gates over rank-one updates to reduce catastrophic forgetting during fine-tuning while adding few parameters.

citing papers explorer

Showing 2 of 2 citing papers.

  • Learning When to Adapt cs.LG · 2026-05-18 · conditional · none · ref 6

    DISeL augments standard LoRA with per-input gates over rank-one updates to reduce catastrophic forgetting during fine-tuning while adding few parameters.

  • PreFT: Prefill-only finetuning for efficient inference cs.LG · 2026-05-14 · accept · none · ref 8

    Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.