English(EN) CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction

新的CA-OPD框架通过置信度感知蒸馏改进视觉语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

研究人员开发了一个名为置信度感知策略内蒸馏（CA-OPD）的新框架，以改进自回归视觉语言模型。该方法通过利用教师置信度来纠正训练过程中不可靠的学生预测，从而解决累积误差问题。CA-OPD将知识转移与干预决策对齐，在纠正的位置提供直接监督，在保留的位置提供完整的预测分布。当应用于GUI定位和光学字符识别任务时，CA-OPD显著增强了Qwen3.5-0.8B基线模型，在ScreenSpot-Pro和OCRBench-v2 English等基准测试中取得了显著的提升。 AI

影响增强了自回归视觉语言模型的性能，可能提高了GUI定位和OCR等任务的准确性。

排序理由该集群描述了在arXiv上发表的学术论文中的一种新方法和框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了在arXiv上发表的学术论文中的一种新方法和框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Menghao Li, Linjie Mu, Yin Wang, Haotian Hu, Yannian Gu, Lujiayi Xue, Fanyi Wang · 2026-09-03 04:00

CA-OPD：面向结构化视觉预测的置信度感知策略内蒸馏

arXiv:2609.02401v1 Announce Type: new Abstract: Autoregressive vision language models unify heterogeneous perception tasks but are highly susceptible to compounding errors. On-policy distillation (OPD) bridges the training-inference mismatch by training students on their own roll…

本文如何被排名

报道来源 [1]

CA-OPD：面向结构化视觉预测的置信度感知策略内蒸馏

相关实体

相关话题