Document Question Answering (DQA) involves generating answers from a document based on a user's query, representing a key task in document understanding.This task requires interpreting visual layouts, which has prompted recent studies to adopt multimodal Retrieval-Augmented Generation (RAG) that processes page images for answer generation.However, in multimodal RAG, visual DQA struggles to utilize a large number of images effectively, as the retrieval stage often retains only a few candidate pages (e.g., Top-4), causing informative but less visually salient content to be overlooked in favor of common yet low-information pages.To address this issue, we propose a Multi-Armed Bandit-based DQA framework (MAB-DQA) to explicitly model the varying importance of multiple implicit aspects in a query.Specifically, MAB-DQA decomposes a query into aspect-aware subqueries and retrieves an aspect-specific candidate set for each.It treats each subquery as an arm and uses preliminary reasoning results from a small number of representative pages as reward signals to estimate aspect utility.Guided by an exploration-exploitation policy, MAB-DQA dynamically reallocates retrieval budgets toward high-value aspects.With the most informative pages and their correlations, MAB-DQA generates the expected results.On four benchmarks, MAB-DQA shows an average improvement of 5%-18% over the state-of-theart method, consistently enhancing document understanding.

Existing multimodal document question-answering (QA) systems predominantly rely on flat semantic retrieval, representing documents as a set of disconnected text chunks and largely neglecting their intrinsic hierarchical and relational structures. Such flattening disrupts logical and spatial dependencies—such as section organization, figure-text correspondence, and cross-reference relations—that humans naturally exploit for comprehension. To address this limitation, we introduce a document-level structural Document MAP (DMAP), which explicitly encodes both hierarchical organization and inter-element relationships within multimodal documents. Specifically, we design a Structured-Semantic Understanding Agent to construct DMAP by organizing textual content together with figures, tables, charts, etc into a human-aligned hierarchical schema that captures both semantic and layout dependencies. Building upon this representation, a Reflective Reasoning Agent performs structure-aware and evidence-driven reasoning, dynamically assessing the sufficiency of retrieved context and iteratively refining answers through targeted interactions with DMAP. Extensive experiments on MMDocQA benchmarks demonstrate that DMAP yields document-specific structural representations aligned with human interpretive patterns, substantially enhancing retrieval precision, reasoning consistency, and multimodal comprehension over conventional RAG-based approaches. Code is available at https://github.com/Forlorin/DMAP

Single-cell RNA sequencing (scRNA-seq) is entering an era of foundation models that accept the complete gene atlas as input, yet most current datasets cover only 10-12 k genes and contain numerous technical zeros, severely limiting the generalization of these models in downstream tasks. To address this, we pioneer the gene-completion task for scRNA-seq and present SAD, a diffusion-based framework tailored to extremely sparse data, capable of completing genes and correcting sparsity bias under high missing rates. Unlike imputation or reconstruction methods that rely on the i.i.d. assumption, SAD's completion paradigm can generate gene entries originally absent from the expression profile, be aware of and rectify sparsity-distribution bias, and supply foundation models with consistent, reliable inputs of more than 30 k genes. Extensive benchmarks show that SAD significantly outperforms existing methods across multiple completion metrics, particularly in extreme scenarios with missing rates above 80%. This provides a data foundation for reusing missing scRNA-seq information and for precision-medicine applications.

Homology among protein sequences plays a crucial role in evolutionary and comparative biology, with a key step involving retrieving homologous sequences of a query or clustering homologous protein sequences within a dataset. However, the growing size of known protein sequences due to advances in sequencing technology has made homologous protein sequence clustering an increasingly challenging task. Current feasible solutions employ locality-sensitive hashing to achieve linear time complexity for sequence clustering. Nonetheless, existing methods do not directly apply this hashing technique based on the foundational concept of edit distance, which precisely defines homology. To address this gap, this paper introduces EdtClust, which aims to design a specific instance of locality-sensitive hashing for edit distance, enhancing clustering efficiency while maintaining a foundation in homology’s essence. EdtClust comprises two core steps: first, utilizing the gapped k-mer embedding framework, it transforms the metric space derived from protein sequences and edit distances into a novel metric space containing gapped k-mer sets and L1distances. Subsequently, a locality-sensitive hashing technique based on the Cauchy distribution is implemented to expedite clustering in this new metric space. Through rigorous theoretical analysis, EdtClust demonstrates enhanced precision and efficiency, while also ensuring a simple and swift implementation. Experimental results using real protein sequences validate that EdtClust can identify more homologous sequence pairs in a shorter time with reduced memory consumption compared to state-of-the-art algorithms like Linclust and ALFATClust, thereby confirming its substantial potential in the field of computational biology.