标签
PixelRAG 是来自伯克利SkyLab等团队的开源项目，通过将网页和PDF截图为截图并用视觉索引进行检索，提高RAG准确率并显著降低AI Agent的token成本。
The paper investigates whether retrieving more evidence helps visual retrieval-augmented generation with diffusion language models, finding that unconditionally expanding evidence hurts accuracy due to semantic conflict, and proposes a training-free Entropy-Based Candidate Filter (ECF) to selectively admit evidence, improving accuracy across benchmarks.
UniDoc-RL 提出了一种面向大型视觉-语言模型的强化学习框架，通过层次化决策与密集多奖励监督来优化检索、重排序和视觉推理，在视觉RAG任务上相较此前基于RL的方法实现了高达17.7%的性能提升。