Recent advancements in multimodal models have significantly improved vision-language (VL) alignment in radiology. However, existing approaches struggle to effectively utilize complex radiology reports for learning and offer limited interpretability through attention probability visualizations. To address these challenges, we introduce $\textbf{RadZero}$, a novel framework for VL alignment in chest X-ray with zero-shot multi-task capability. A key component of our approach is $\textbf{VL-CABS}$ ($\textbf{V}$ision-$\textbf{L}$anguage $\textbf{C}$ross-$\textbf{A}$ttention $\textbf{B}$ased on $\textbf{S}$imilarity), which aligns text embeddings with local image features for interpretable, fine-grained VL reasoning. RadZero leverages large language models to extract concise semantic sentences from radiology reports and employs multi-positive contrastive training to effectively capture relationships between images and multiple relevant textual descriptions. It uses a pre-trained vision encoder with additional trainable Transformer layers, allowing efficient high-resolution image processing. By computing similarity between text embeddings and local image patch features, VL-CABS enables zero-shot inference with similarity probability for classification, and pixel-level VL similarity maps for grounding and segmentation. Experimental results on public chest radiograph benchmarks show that RadZero outperforms state-of-the-art methods in zero-shot classification, grounding, and segmentation. Furthermore, VL similarity map analysis highlights the potential of VL-CABS for improving explainability in VL alignment. Additionally, qualitative evaluation demonstrates RadZero's capability for open-vocabulary semantic segmentation, further validating its effectiveness in medical imaging. Code is available at https://github.com/deepnoid-ai/RadZero.

The rapid evolution of artificial intelligence, especially in large language models (LLMs), has significantly impacted various domains, including healthcare. In chest X-ray (CXR) analysis, previous studies have employed LLMs, but with limitations: either underutilizing the LLMs' capability for multitask learning or lacking clinical accuracy. This article presents M4CXR, a multimodal LLM designed to enhance CXR interpretation. The model is trained on a visual instruction-following dataset that integrates various task-specific datasets in a conversational format. As a result, the model supports multiple tasks such as medical report generation (MRG), visual grounding, and visual question answering (VQA). M4CXR achieves state-of-the-art clinical accuracy in MRG by employing a chain-of-thought (CoT) prompting strategy, in which it identifies findings in CXR images and subsequently generates corresponding reports. The model is adaptable to various MRG scenarios depending on the available inputs, such as single-image, multiimage, and multistudy contexts. In addition to MRG, M4CXR performs visual grounding at a level comparable to specialized models and demonstrates outstanding performance in VQA. Both quantitative and qualitative assessments reveal M4CXR's versatility in MRG, visual grounding, and VQA, while consistently maintaining clinical accuracy.

Inspired by common features found in collaborative behaviors in nature, we investigate a general collaborative pursuit framework enabling heterogeneous multi-robot systems to adapt to dynamic environments and diverse tasks. A class of augmented Fokker-Planck equations is formulated to characterize dynamic environmental conditions, and the resulting time-varying density functions drive a novel coverage-based controller, with provable stability properties, for the participating robots to perform tasks in real time. The developed framework is decentralized and incorporates heterogeneity among different robots in task suitability, relative performance in a specific task, and safe operating regions. To demonstrate its adaptivity and effectiveness, the framework is implemented across four experimental applications ranging from multi-robot coordination to collaboration, namely forest firefighting, pursuit-evasion, monitoring of various environmental phenomena, and phoretic interactions.