AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Developmental Federated Tuning: A Cognitive-Inspired Paradigm for Efficient LLM Adaptation

Yebo Wu, Jingguang Li, Zhijiang Guo, Li Li

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add deconfliction-guided layer grouping instead of random grouping (ablation)DEVFT (LLaMA2-7B) · Close-ended averageaverage accuracy: 39.90 -> 42.33Improved
add deconfliction-guided layer grouping instead of even grouping (ablation)DEVFT (LLaMA2-7B) · Close-ended averageaverage accuracy: 36.25 -> 42.33Improved
add deconfliction-guided layer grouping instead of random grouping (ablation)DEVFT (LLaMA3.1-8B) · Close-ended averageaverage accuracy: 60.69 -> 64.25Improved
add deconfliction-guided layer grouping instead of even grouping (ablation)DEVFT (LLaMA3.1-8B) · Close-ended averageaverage accuracy: 57.76 -> 64.25Improved
add differential-based layer fusion instead of random single-layer representative (ablation)DEVFT (LLaMA2-7B) · Close-ended averageaverage accuracy: 37.72 -> 42.33Improved
add differential-based layer fusion instead of summing all group layers (ablation)DEVFT (LLaMA2-7B) · Close-ended averageaverage accuracy: 40.90 -> 42.33Improved
add differential-based layer fusion instead of random single-layer representative (ablation)DEVFT (LLaMA3.1-8B) · Close-ended averageaverage accuracy: 53.29 -> 64.25Improved
add differential-based layer fusion instead of summing all group layers (ablation)DEVFT (LLaMA3.1-8B) · Close-ended averageaverage accuracy: 61.20 -> 64.25Improved
use initial submodel capacity 4 instead of 1 (ablation)DEVFT (LLaMA3.1-8B) · Close-ended averageaverage accuracy: 61.56 -> 64.25Improved
use initial submodel capacity 4 instead of 32 (ablation)DEVFT (LLaMA3.1-8B) · Close-ended averageaverage accuracy: 58.09 -> 64.25Improved
use growth rate 2 instead of 4 (ablation)DEVFT (LLaMA2-13B) · Close-ended averageaverage accuracy: 46.47 -> 52.77Improved
use growth rate 2 instead of 8 (ablation)DEVFT (LLaMA2-7B) · Close-ended averageaverage accuracy: 37.08 -> 42.33Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy