Text logo design heavily relies on the creativity and expertise of professional designers, in which arranging element layouts is one of the most important procedures. However, this specific task has received limited attention, often overshadowed by broader layout generation tasks such as document or poster design. In this paper, we propose a Vision-Language Model (VLM)-based framework that generates content-aware text logo layouts by integrating multi-modal inputs with user-defined constraints, enabling more flexible and robust layout generation for real-world applications. We introduce two model techniques that reduce the computational cost for processing multiple glyph images simultaneously, without compromising performance. To support instruction tuning of our model, we construct two extensive text logo datasets that are five times larger than existing public datasets. In addition to geometric annotations (e.g., text masks and character recognition), our datasets include detailed layout descriptions in natural language, enabling the model to reason more effectively in handling complex designs and custom user inputs. Experimental results demonstrate the effectiveness of our proposed framework and datasets, outperforming existing methods on various benchmarks that assess geometric aesthetics and human preferences.

Real-time electroencephalography (EEG) offers a more objective foundation for diagnosing depression compared to alternative methodologies. Our research introduces AstrocyteSNN (Astrocyte Spiking Neural Network), an innovative approach that enhances EEG signal recognition by leveraging astrocytic calcium waves to establish long-range connections. AstrocyteSNN demonstrates superior performance in managing long-range dependencies and integrating global information compared to conventional spiking neural networks (SNNs), while maintaining low energy consumption. The model shows promise for early depression diagnosis and monitoring.

Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose AnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation empowers users with greater flexibility to engage with the model beyond textual and regional prompts, without modality-specific designs. Through our proposed refocusing mechanism, the generated grounding output is guided to better focus on the referenced object, implicitly incorporating additional pixel-level supervision. This simple modification utilizes attention scores generated during the inference of LLM, eliminating the need for extra computations while exhibiting performance enhancements in both grounding masks and referring expressions. With only publicly available training data, our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation. Code and models are available at https://github.com/jwh97nn/AnyRef

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a persegment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels. Code and models are available at https://github.com/jwh97nn/DeepDPS.

In recent years, important progress has been made in developing design strategies, materials, and associated assembly techniques that provide empowering approaches to electronics with unconventional formats, ones that allow useful but previously hard to realize attributes of function. Notable examples of the progress made include: light weight, large area, high performance electronics, optics, and photonics; electronic and optical systems with curvilinear shapes and capacities for accommodating demanding forms of mechanical flexure; new device form factors for use in sensing and imaging; the integration of high performance electronics in 3-D with demanding nanometer design rules; functional bioresponsive electronics; and advanced hybrid materials systems for lighting, energy storage, and photovoltaic energy conversion. In this report we highlight advances that are enabling such promising capabilities in technology-specifically, the fabrication of device elements using high performance inorganic electronic materials joined with printing and transfer methods to effect their integration within functional modules. We emphasize in this review considerations of the design strategies and assembly techniques that, when taken together, circumvent limitations imposed by approaches that integrate circuit elements within compact, rigid, and essentially planar form factor devices, and provide a transformational set of capabilities for high performance flexible/stretchable electronics.