AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air

[2507.11515] AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2507.11515 (cs) [Submitted on 15 Jul 2025 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air Authors: Shiyi Yang , Xiaoxue Yu , Rongpeng Li , Jianhang Zhu , Zhifeng Zhao , Honggang Zhang View PDF HTML (experimental) Abstract: Operating Large Language Models (LLMs) on edge devices is increasingly challenged by limited communication bandwidth and strained computational and memory costs. Thus, cloud-assisted remote fine-tuning becomes indispensable. Nevertheless, existing Low-Rank Adaptation (LoRA) approaches typically employ fixed or heuristic rank configurations, and the subsequent over-the-air transmission of all LoRA parameters could be rather inefficient. To address this limitation, we develop AirLLM, a hierarchical diffusion policy framework for communication-aware LoRA adaptation. Specifically, AirLLM models the rank configuration as a structured action vector that spans all LoRA-inserted projections. To solve the underlying high-dimensional sequential decision-making problem, a Proximal Policy Optimization (PPO) agent generates coarse-grained decisions by jointly observing wireless states and linguistic complexity, which are then refined via Denoising Diffusion Implicit Models (DDIM) to produce high-resolution, task- and channel-adaptive rank vectors. The two modules are optimized alternatively, with the DDIM trained under the Classifier-Free Guidance (CFG) paradigm to maintain alignment with PPO rewards. Experiments under varying signal-to-noise ratios demonstrate that AirLLM consistently enhances fine-tuning performance while significantly reducing transmission costs, highlighting the effectiveness of reinforcement-driven, diffusion-refined rank adaptation for scalable and efficient remote fine-tuning over the air. Comments: 11 pages, 8 figures Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2507.11515 [cs.LG] (or arXiv:2507.11515v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2507.11515 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Shiyi Yang [ view email ] [v1] Tue, 15 Jul 2025 17:36:37 UTC (921 KB) [v2] Thu, 27 Aug 2026 03:41:04 UTC (921 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2025-07 Change to browse by: cs cs.AI cs.CL References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air#677394
• RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks#819555
• RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks#809559
• Supplementary file 1_Application-driven pedagogical knowledge optimization of open-source LLMs via reinforcement learning and supervised fine-tuning.pdf#325675
• SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs#1156287