← Back to all news
arXiv Computer Vision By Menghao Li, Linjie Mu, Yin Wang, Haotian Hu, Yannian Gu, Lujiayi Xue, Fanyi Wang

CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction

Read the original on arXiv Computer Vision →

CA-OPD is a confidence‑aware on‑policy distillation framework that improves structured visual prediction by using teacher confidence to selectively correct unreliable student transitions and gradually transfer rollout control to the student. The method aligns supervision with intervention decisions, providing direct cross‑entropy loss for corrected tokens and full predictive distribution for retained tokens. In a multi‑teacher setting for GUI grounding and OCR, CA‑OPD significantly outperforms the Qwen3.5‑0.8B baseline, achieving large gains on benchmarks such as ScreenSpot‑Pro and OCRBench‑v2 English.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Oct 16

Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models

The paper investigates how on‑policy distillation (OPD) inherits a teacher’s behavior in vision‑language models, comparing it to filtered supervised fine‑tuning (SFT) across different data budgets and tasks. Experiments on ChartQA and Geometry3K show that OPD performs well only when the teacher remains reliable on student‑generated trajectories; otherwise it underperforms SFT and can erase previously learned completion behavior. Filtering teacher demonstrations for completeness largely restores SFT’s advantages, indicating that OPD can transfer both knowledge and persistent failure modes from the teacher.

By Frank F. Yang, Kefei Yan, Yiren Wang, Yiyang Wang
llmsfine-tuningefficiencymultimodal
More like this →