Heirloom: Carrying a Phone's Personalization Across Base-Model Generations
cs.LG, cs.CL
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
- Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Training
- Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
- TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models
- Distilling the Knowledge in a Neural Network
- TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- FedMD: Heterogenous Federated Learning via Model Distillation
- LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
- LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
- Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
- Qwen3 Technical Report
- First-Order LoRA Training with Phone NPUs
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis