Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing

Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit.

AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models

Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control, yet most existing approaches primarily rely on VLM trained using 2D images, which limits their spatial understanding and action grounding in complex 3D environments. To address this limitation, we propose a novel framework that integrates depth estimation into VLA models to enrich 3D feature representations. Specifically, we employ a depth estimation baseline called VGGT to extract geometry-aware 3D cues from standard RGB inputs, enabling efficient utilization of existing large-scale 2D datasets while implicitly recovering 3D structural information. To further enhance the reliability of these depth-derived features, we introduce a new module called action assistant, which constrains the learned 3D representations with action priors and ensures their consistency with downstream control tasks. By fusing the enhanced 3D features with conventional 2D visual tokens, our approach significantly improves the generalization ability and robustness of VLA models. Experimental results demonstrate that the proposed method not only strengthens perception in geometrically ambiguous scenarios but also leads to superior action prediction accuracy. This work highlights the potential of depth-driven data augmentation and auxiliary expert supervision for bridging the gap between 2D observations and 3D-aware decision-making in robotic systems.

Dynamic Scene Deblurring Base on Continuous Cross-Layer Attention Transmission

The deep convolutional neural networks (CNNs) using attention mechanism have achieved great success for dynamic scene deblurring. In most of these networks, only the features refined by the attention maps can be passed to the next layer and the attention maps of different layers are separated from each other, which does not make full use of the attention information from different layers in the CNN. To address this problem, we introduce a new continuous cross-layer attention transmission (CCLAT) mechanism that can exploit hierarchical attention information from all the convolutional layers. Based on the CCLAT mechanism, we use a very simple attention module to construct a novel residual dense attention fusion block (RDAFB). In RDAFB, the attention maps inferred from the outputs of the preceding RDAFB and each layer are directly connected to the subsequent ones, leading to a CRLAT mechanism. Taking RDAFB as the building block, we design an effective architecture for dynamic scene deblurring named RDAFNet. The experiments on benchmark datasets show that the proposed model outperforms the state-of-the-art deblurring approaches, and demonstrate the effectiveness of CCLAT mechanism. The source code is available on: https://github.com/xjmz6/RDAFNet.