Tag
该论文系统研究了混合模态检索器的模态偏好问题，发现无关文本比无关图像对检索性能的干扰更严重（称为 "Chaos in the Text"），并提出 Trident 方法，通过 Multi-Positive View InfoNCE 联合优化文本、图像和融合视图来缓解该偏差。
NeoMME presents a family of efficient multimodal encoders pretrained with masked discrete diffusion, achieving strong performance in visual document retrieval and high embedding compression while outperforming smaller models on benchmarks.
RetrievalRouter is a lightweight query-aware router that adaptively selects retrieval pipelines to improve accuracy and speed in document retrieval, outperforming static baselines.
The paper proposes Trident, a method that enhances long-document visual question answering through structured multi-aspect page annotation for reranking and synthesis, improving evidence selection and answer generation accuracy.
LlamaParse introduces new document retrieval endpoints including hybrid search, file grep, file find, and file read, aiming to improve agentic retrieval quality over unstructured documents.
A detailed technical query about building a local document RAG system covering storage, ingestion, query, and highlighting, seeking advice on vector databases, GraphRAG feasibility, and document highlighting implementations.
Unveil introduces a unified visual-textual embedding framework for multi-modal document retrieval, using knowledge distillation to transfer semantic understanding from a visual-textual model to a purely visual model, achieving robust and efficient retrieval.
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.