MobileFlow: A Multimodal LLM For Mobile GUI Agent

Currently, the integration of mobile Graphical User Interfaces (GUIs) is ubiquitous in most people's daily lives. And the ongoing evolution of multimodal large-scale models, such as GPT-4v, Qwen-VL-Max, has significantly bolstered the capabilities of GUI comprehension and user action analysis, showcasing the potentiality of intelligent GUI assistants. However, current GUI Agents often need to access page layout information through calling system APIs, which may pose privacy risks. Fixing GUI (such as mobile interfaces) to a certain low resolution might result in the loss of fine-grained image details. At the same time, the multimodal large models built for GUI Agents currently have poor understanding and decision-making abilities for Chinese GUI interfaces, making them difficult to apply to a large number of Chinese apps. This paper introduces MobileFlow, a multimodal large language model meticulously crafted for mobile GUI agents. Transforming from the open-source model Qwen-VL-Chat into GUI domain, MobileFlow contains approximately 21 billion parameters and is equipped with novel hybrid visual encoders, making it possible for variable resolutions of image inputs and good support for multilingual GUI. By incorporating Mixture of Experts (MoE) expansions and pioneering alignment training strategies, MobileFlow has the capacity to fully interpret image data and comprehend user instructions for GUI interaction tasks. Finally, MobileFlow outperforms Qwen-VL-Max and GPT-4v in terms of task execution by GUI agents on both public and our proposed evaluation metrics, and has been successfully deployed in real-world business contexts, proving its effectiveness for practical applications.

PREMA: Part-based REcurrent Multi-view Aggregation Network for 3D Shape Retrieval

We propose the Part-based Recurrent Multi-view Aggregation network(PREMA) to eliminate the detrimental effects of the practical view defects, such as insufficient view numbers, occlusions or background clutters, and also enhance the discriminative ability of shape representations. Inspired by the fact that human recognize an object mainly by its discriminant parts, we define the multi-view coherent part(MCP), a discriminant part reoccurring in different views. Our PREMA can reliably locate and effectively utilize MCPs to build robust shape representations. Comprehensively, we design a novel Regional Attention Unit(RAU) in PREMA to compute the confidence map for each view, and extract MCPs by applying those maps to view features. PREMA accentuates MCPs via correlating features of different views, and aggregates the part-aware features for shape representation.

RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes

We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research. The new dataset contains the largest number of rainy images (58,542) to date, 5,000 of which provide semantic segmentations and 3,658 provide object instance segmentations. The RaidaR images cover a wide range of realistic rain-induced artifacts, including fog, droplets, and road reflections, which can effectively augment existing street scene datasets to improve data-driven machine perception during rainy weather. To facilitate efficient annotation of a large volume of images, we develop a semi-automatic scheme combining manual segmentation and an automated processing akin to cross validation, resulting in 10-20 fold reduction on annotation time. We demonstrate the utility of our new dataset by showing how data augmentation with RaidaR can elevate the accuracy of existing segmentation algorithms. We also present a novel unpaired image-to-image translation algorithm for adding/removing rain artifacts, which directly benefits from RaidaR.

DR-KFD: A Differentiable Visual Metric for 3D Shape Reconstruction

We advocate the use of differential visual shape metrics to train deep neural networks for 3D reconstruction. We introduce such a metric which compares two 3D shapes by measuring visual, image-space differences between multiview images differentiably rendered from the shapes. Furthermore, we develop a differentiable image-space distance based on mean-squared errors defined over Hard- Net features computed from probabilistic keypoint maps of the compared images. Our differential visual shape metric can be easily plugged into various reconstruction networks, replacing the object-space distortion measures, such as Chamfer or Earth Mover distances, so as to optimize the network weights to produce reconstruction results with better structural fidelity and visual quality. We demonstrate this both objectively, using well-known visual shape metrics for retrieval and classification tasks that are independent from our new metric, and subjectively through a perceptual study.