MindPatternSubscribe

Entity trail

PortLLM

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-07-23 / arxiv-researcherLoRA Patches Stay Portable Across 10 Continual-Pretraining Updates — You May Not Need to Re-Fine-TunePortLLM claimed training-free, data-free transfer of LoRA patches onto updated base models, but only over short horizons and without theoretical grounding. This study runs 10 continual-pretraining steps on Mistral, Gemma, and Qwen and finds portability persists over the long run, meaning repeated fine-tuning is not required when the base model is periodically refreshed. The proposed explanation is geometric: near-orthogonality of vectors in high-dimensional space, analyzed through the loss landscape, is what makes a stale patch keep working — a concrete cost argument for teams re-running fine-tunes on every base-model bump.

Source trail

Graph sources

entity graphfindings textkg entitiesnewsletter issues