Multi‑page Document Visual Question Answering (MP‑DocVQA) remains challenging because long documents not only strain computational resources but also reduce the effectiveness of the attention mechanism in large vision–language models (LVLMs). We tackle these issues with an Adaptive Visual In‑document Retrieval (AVIR) framework. A lightweight retrieval model first scores each page for question relevance. Pages are then clustered according to the score distribution to adaptively select relevant content. The clustered pages are screened again by Top-K to keep the context compact. However, for short documents, clustering reliability decreases, so we use a relevance probability threshold to select pages. The selected pages alone are fed to a frozen LVLM for answer generation, eliminating the need for model fine‑tuning. The proposed AVIR framework reduces the average page count required for question answering by 70%, while achieving an ANLS of 84.58% on the MP-DocVQA dataset—surpassing previous methods with significantly lower computational cost. The effectiveness of the proposed AVIR is also verified on the SlideVQA and DUDE benchmarks. Our code will be made publicly available upon acceptance.

Transformer-based models have made significant progress in edge detection, but their high computational cost is prohibitive. Recently, vision Mamba have shown excellent ability in efficiently capturing long-range dependencies. Drawing inspiration from this, we propose a novel edge detector with Mamba, termed EDMB, to efficiently generate high-quality multi-granularity edges. In EDMB, Mamba is combined with a global-local architecture, therefore it can focus on both global information and fine-grained cues. The fine-grained cues play a crucial role in edge detection, but are usually ignored by ordinary Mamba. We design a novel decoder to construct learnable Gaussian distributions by fusing global features and fine-grained features. And the multi-grained edges are generated by sampling from the distributions. In order to make multi-granularity edges applicable to single-label data, we introduce Evidence Lower Bound loss to supervise the learning of the distributions. On the multi-label dataset BSDS500, our proposed EDMB achieves competitive single-granularity ODS 0.837 and multi-granularity ODS 0.851 without multi-scale test or extra PASCAL-VOC data. Remarkably, EDMB can be extended to single-label datasets such as NYUDv2 and BIPED. The source code is available at https://github.com/Li-yachuan/EDMB.

Smoothing of the graph convolution is not conducive to characterizing local differences of point cloud. To solve this problem, we propose a Differential Graph Convolutional Network (Differ-GCN) for point cloud analysis. First, we propose a new graph construction strategy that can make similar nodes in the local space belong to the same graph, which can better represent the local commonality. After that, the features of the graph are extracted by the similarity matrix. Some of the smoothing information of the graph is removed to optimize the over-smoothing nodes and combined with the local difference of the points to get the beneficial features for downstream tasks. Finally, each neighbor point is processed to generate a mask, and pooling is performed through the mask to reduce information loss. The experiment results show that Differ-GCN performs excellent in object classification and part segmentation. The processing speed of Differ-GCN for point cloud is much faster than the state-of-the-art methods.