Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

YOLO-PEFT: A Structure-Aware Framework for Parameter-Efficient Fine-Tuning of Real-Time Detectors

AI By Crimson AI Hugging Face Papers 10 August 2026 · 00:00 13 views
Share: X Telegram

Researchers propose YOLO-PEFT, a framework that treats adapter placement as an auditable constraint-planning problem, outperforming full fine-tuning on YOLO11s and YOLO12s while reducing memory usage by 43.9%.

YOLO-PEFT: A Structure-Aware Framework for Parameter-Efficient Fine-Tuning of Real-Time Detectors

Key points

Generic parameter-efficient fine-tuning (PEFT) methods, originally designed for language models, often fail silently when applied to real-time object detectors. These detectors contain heterogeneous operators and detection-specific components that impose placement constraints not found in standard Transformer stacks. To address this, researchers from Tencent introduced YOLO-PEFT, a structure-aware framework that formulates adapter placement as an auditable constraint-planning problem.

The framework takes a detector graph, a PEFT request, and a resource budget as input. It assigns operator and semantic roles, evaluates explicit predicates for operator validity, detector semantics, graph interfaces, and deployment requirements, and records a reason code for each excluded module. The system then either emits a budgeted target-module plan or returns Refuse before training begins, ensuring that only viable configurations proceed.

Under the official VOC07+12 trainval-to-VOC07 test protocol, planner-selected RS-LoRA achieved 0.7138 mAP50-95 on YOLO11s and 0.7307 on YOLO12s, compared with 0.6428 and 0.6662 for full fine-tuning (Full-SFT). On RT-DETR-L, all seven evaluated LoRA-family configurations crossed a predefined catastrophic threshold, supporting a calibrated Refuse-to-Full-SFT decision within the evaluated coverage.

A controlled audit on YOLO11 showed that LoRA reduces peak training memory by 43.9%, though training takes 1.72 times longer. The framework replaces manual trial-and-error with explicit, inspectable planning while preserving verified train-save-merge-export paths. However, refusal on unseen detector architectures remains an open validation problem.

ModelMethodmAP50-95
YOLO11sRS-LoRA (planner-selected)0.7138
YOLO11sFull-SFT0.6428
YOLO12sRS-LoRA (planner-selected)0.7307
YOLO12sFull-SFT0.6662
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1