Tag
PixelRAG is an open-source project from UC Berkeley SkyLab and other teams. By capturing web pages and PDFs as screenshots and using visual indexing for retrieval, it improves RAG accuracy and significantly reduces token costs for AI Agents.
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 presents a reinforcement learning framework for Large Vision-Language Models that optimizes retrieval, reranking, and visual reasoning through hierarchical decision-making and dense multi-reward supervision, achieving up to 17.7% improvements over prior RL-based methods on visual RAG tasks.