cs.LGOct 31, 2026

Heirloom: Carrying a Phone's Personalization Across Base-Model Generations

Authors: Zhuomin Chen, Jingchao Ni, Qingkai Dong, Xu Zheng, Gabriel Hübner Lucchesi, Mo Sha, Wei Cheng, Dongsheng Luo

Organizations: Florida International University, Miami, FL, USA · University of Houston, Houston, TX, USA · University of Connecticut, Storrs, CT, USA · Independent Researcher, USA · 

Abstract

On-device language models can learn a user's preferences through adapters trained on private data. However, a base-model upgrade may change the layers or vocabulary, leaving the personal adapter incompatible. Replacing it with a non-personal adapter loses much of the personalization, while retraining requires retaining the user's labeled history. We present Heirloom, a system that transfers a personal adapter to a new base model on the phone without retaining labels. Heirloom uses the old personal model as a teacher, collecting its predictions on stored unlabeled inputs, vendor-provided prompts, or prompts generated by the new base. It then unloads the old base and trains an adapter for the new model to match those predictions, keeping only one base model in memory at a time. We evaluate Heirloom across three generation upgrades from two model families, an architecture-preserving refresh, and three personalization tasks. On movie tagging, migration from stored inputs maintains pre-upgrade accuracy and differs from labeled retraining by at most 1.7 percentage points across the three upgrades. On a phone's neural processing unit (NPU), a fixed-length migration for the 4B upgrade takes 38 minutes and consumes 20% of the battery end to end, making the stored-input setting feasible during overnight charging.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 5, 2026

Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Training

Multi-billion-parameter LLMs now run on phones for inference, and training them on the device would personalize them without user data leaving the phone. Prior work has measured individual training steps of such models on phones, but not complete training runs, and not whether adapters trained on the device improve personalization. We present the first systematic characterization of a multi-billion-parameter LLM fine-tuned on a mobile device, covering memory, per-step time, thermal behavior, and energy. An iPhone 17 Pro can fine-tune a 3B-parameter LLM to a typical user within one battery charge, and the resulting adapters improve personalization as much as adapters trained on a server. Sustained training throttles the phone to about half its initial throughput, and none of the pausing or burst schedules we tested recovers it. Nearly all of each training step is spent in the frozen base model, most of it in the backward pass, which nine of the ten other runtimes we audited do not accelerate. Apple's MLX had a kernel for it that was never dispatched and was incorrect, and our repair, now merged upstream, trains an adapter 1.47x faster on a third less energy. On-device fine-tuning is feasible on current phones, and making it efficient requires runtimes and operating systems to treat training as a first-class workload.
Aug 21, 2026

UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists

Organizations maintain task-specific adapters for open-weight language models, and each new base-model release forces a migration decision: retain existing specialists, port adapters, refresh from preserved behavior, or retrain. Prior transfer work evaluates isolated model pairs, without studying these choices across real model release sequences. We present UpgradeBench, a decision-driven longitudinal benchmark covering four consecutive Qwen releases, one continuation checkpoint, six tasks, and two model sizes, augmented by OLMo checkpoints with known training lineage. The benchmark disentangles three core questions: whether a new checkpoint improves fixed-recipe retrained specialist performance, whether specialization assets transfer across versions, and what recovery resources are usable. We observe upgrade gains differ across task-scale-release episodes: some retrained baselines improve while others stay within training noise, with durability ranging from under one release interval for text-to-SQL to over fourteen months for intent classification. Direct adapter copying depends neither on architecture nor model family: on OLMo, retention drops from 0.88-0.99 at 46B-token continued pretraining to zero at 2.9T tokens; annealing and model souping introduce no extra harm, with portability decaying with continued-pretraining distance. Given preserved input data, teacher relabeling recovers target-base specialists without fresh gold annotations, though compute savings are not guaranteed. Simulating a fixed decision policy over 33 upgrade episodes yields 0.37pp mean quality regret with zero behavioral regressions at one-third the compute and label cost of full retraining. A lightweight CKA probe over 256 prompts predicts cross-version adapter portability (Spearman 0.74 across eight model pairs). We release per-example predictions, cost logs, split manifests, and evaluation code.
Oct 17, 2026

First-Order LoRA Training with Phone NPUs

On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable parameters, but each first-order training step still multiplies by the frozen base-model weights during the forward pass, activation recomputation, and input-gradient computation. A phone's neural processing unit (NPU) already holds these weights for inference; using it for training also requires computing input gradients, which its inference interface does not support. We present a system that runs all three frozen-weight products on the NPU while keeping the training graph, adapters, and optimizer on the CPU. Its input-gradient kernels reuse the resident weight tiles and the forward dequantizer, avoiding a transposed weight copy and ensuring forward and backward use the same effective weights. To preserve usable gradients, the system selects precision by gradient sensitivity and applies a per-row range guard for half-precision (FP16) outputs. Its runtime fuses the remaining CPU operators and overlaps NPU execution with adapter computation, while resumable execution and thermal pacing let training proceed as a background job. We evaluate it on two Qualcomm Snapdragon platforms using four LLMs from the Qwen and Llama families. Our workloads cover nightly personalization with labels supplied on the phone and the public LaMP-2 benchmark; comparisons include an optimized CPU trainer, a phone-GPU trainer, forward-only training, and GPU-trained references.