arXiv Computer Science @arxiv_cs@qoto.org

Multi-modal large language models (MLLMs) have recently achieved great success in processing and understanding information from diverse modalities (e.g., text, audio, and visual signals). Despite their growing popularity, there remains a lack of comprehensive evaluation measuring the audio-visual capabilities of these models, especially in diverse scenarios (e.g., distribution shifts and adversarial attacks). In this paper, we present a multifaceted evaluation of the audio-visual capability of MLLMs, focusing on four key dimensions: effectiveness, efficiency, generalizability, and robustness. Through extensive experiments, we find that MLLMs exhibit strong zero-shot and few-shot generalization abilities, enabling them to achieve great performance with limited data. However, their success relies heavily on the vision modality, which impairs performance when visual input is corrupted or missing. Additionally, while MLLMs are susceptible to adversarial samples, they demonstrate greater robustness compared to traditional models. The experimental results and our findings provide insights into the audio-visual capabilities of MLLMs, highlighting areas for improvement and offering guidance for future research.

The increasing adoption of cryptocurrencies has significantly amplified the resource requirements for operating full nodes, creating substantial barriers to entry. Unlike miners, who are financially incentivized through block rewards and transaction fees, full nodes lack direct economic compensation for their critical role in maintaining the network. A key resource burden is the transaction pool, which is particularly memory-intensive as it temporarily stores unconfirmed transactions awaiting verification and propagation across the network. We present Neonpool, a novel optimization for transaction pool leveraging bloom filter variants to drastically reduce memory consumption by up to 200 (e.g., 400 MB to 2 MB) while maintaining over 99.99% transaction processing accuracy. Implemented in C++ and evaluated on unique Bitcoin and Ethereum datasets, Neonpool enables efficient operation on lightweight clients, such as smartphones, IoT devices, and systems-on-a-chip, without requiring a hard fork. By lowering the cost of node participation, Neonpool enhances decentralization and strengthens the overall security and robustness of cryptocurrency networks.

Backgrounds: Artificial intelligence (AI) is transforming healthcare, yet translating AI models from theoretical frameworks to real-world clinical applications remains challenging. The Mayo Clinic Platform (MCP) was established to address these challenges by providing a scalable ecosystem that integrates real-world multiple modalities data from multiple institutions, advanced analytical tools, and secure computing environments to support clinical research and AI development. Methods: In this study, we conducted four research projects leveraging MCP's data infrastructure and analytical capabilities to demonstrate its potential in facilitating real-world evidence generation and AI-driven clinical insights. Utilizing MCP's tools and environment, we facilitated efficient cohort identification, data extraction, and subsequent statistical or AI-powered analyses. Results: The results underscore MCP's role in accelerating translational research by offering de-identified, standardized real-world data and facilitating AI model validation across diverse healthcare settings. Compared to Mayo's internal Electronic Health Record (EHR) data, MCP provides broader accessibility, enhanced data standardization, and multi-institutional integration, making it a valuable resource for both internal and external researchers. Conclusion: Looking ahead, MCP is well-positioned to transform clinical research through its scalable ecosystem, effectively bridging the divide between AI innovation and clinical deployment. Future investigations will build upon this foundation, further exploring MCP's capacity to advance precision medicine and enhance patient outcomes.

Homomorphic Encryption (HE) allows secure and privacy-protected computation on encrypted data without the need to decrypt it. Since Shor's algorithm rendered prime factorisation and discrete logarithm-based ciphers insecure with quantum computations, researchers have been working on building post-quantum homomorphic encryption (PQHE) algorithms. Most of the current PQHE algorithms are secured by Lattice-based problems and there have been limited attempts to build ciphers based on error-correcting code-based problems. This review presents an overview of the current approaches to building PQHE schemes and justifies code-based encryption as a novel way to diversify post-quantum algorithms. We present the mathematical underpinnings of existing code-based cryptographic frameworks and their security and efficiency guarantees. We compare lattice-based and code-based homomorphic encryption solutions identifying challenges that have inhibited the progress of code-based schemes. We finally propose five new research directions to advance post-quantum code-based homomorphic encryption.

Cooperative speech is purposive. From the speaker's perspective, one crucial purpose is the transmission of knowledge. Cooperative speakers care about getting things right for their conversational partners. This attitude is a kind of respect. Cooperative speech is an ideal form of communication because participants have respect for each other. And having respect within a cooperative enterprise is sufficient for a particular kind of moral standing: we ought to respect those who have respect for us. Respect demands reciprocity. I maintain that large language models aren't owed the kind of respect that partly constitutes a cooperative conversation. This implies that they aren't cooperative interlocutors, otherwise we would be obliged to reciprocate the attitude. Leveraging this conclusion, I argue that present-day LLMs are incapable of assertion and that this raises an overlooked doubt about their semantic competence. One upshot of this argument is that knowledge of meaning isn't just a subject for the cognitive psychologist. It's also a subject for the moral psychologist.

Neural radiance fields (NeRFs) have recently attracted significant attention in the field of wireless channel prediction, primarily due to their capability for high-fidelity reconstruction of complex wireless measurement environments. However, the ray-tracing component of NeRF-based methods faces challenges in realistically representing wireless scenarios, mainly due to the limited expressive power of multilayer perceptrons (MLPs). To overcome this issue, in this paper, we propose NeRF-APT, an encoder-decoder architecture integrated within a NeRF-based wireless channel prediction framework. Our architecture leverages the strengths of NeRF-like models in learning environmental features and exploits encoder-decoder modules' capabilities for critical information extraction. Additionally, we incorporate an attention mechanism within the skip connections between encoder and decoder layers, significantly enhancing contextual understanding across layers. Extensive experimental evaluations conducted on several realistic and synthetic datasets demonstrate that our proposed method outperforms existing state-of-the-art approaches in wireless channel prediction.

Idling vehicle detection (IVD) supports real-time systems that reduce pollution and emissions by dynamically messaging drivers to curb excess idling behavior. In computer vision, IVD has become an emerging task that leverages video from surveillance cameras and audio from remote microphones to localize and classify vehicles in each frame as moving, idling, or engine-off. As with other cross-modal tasks, the key challenge lies in modeling the correspondence between audio and visual modalities, which differ in representation but provide complementary cues -- video offers spatial and motion context, while audio conveys engine activity beyond the visual field. The previous end-to-end model, which uses a basic attention mechanism, struggles to align these modalities effectively, often missing vehicle detections. To address this issue, we propose AVIVDNetv2, a transformer-based end-to-end detection network. It incorporates a cross-modal transformer with global patch-level learning, a multiscale visual feature fusion module, and decoupled detection heads. Extensive experiments show that AVIVDNetv2 improves mAP by 7.66 over the disjoint baseline and 9.42 over the E2E baseline, with consistent AP gains across all vehicle categories. Furthermore, AVIVDNetv2 outperforms the state-of-the-art method for sounding object localization, establishing a new performance benchmark on the AVIVD dataset.

Code editing is a foundational task in software development, where its effectiveness depends on whether it introduces desired code property changes without changing the original code's intended functionality. Existing approaches often formulate code editing as an implicit end-to-end task, omitting the fact that code-editing procedures inherently consist of discrete and explicit steps. Thus, they suffer from suboptimal performance and lack of robustness and generalization. We introduce EditLord, a code editing framework that makes the code transformation steps explicit. Our key insight is to employ a language model (LM) as an inductive learner to extract code editing rules from the training code pairs as concise meta-rule sets. Such rule sets will be manifested for each training sample to augment them for finetuning or assist in prompting- and iterative-based code editing. EditLordoutperforms the state-of-the-art by an average of 22.7% in editing performance and 58.1% in robustness while achieving 20.2% higher functional correctness across critical software engineering and security applications, LM models, and editing modes.

This paper presents an approach to automating JUnit test generation for Java applications using the Spring Boot framework, leveraging the LLaMA (Large Language Model Architecture) model to enhance the efficiency and accuracy of the testing process. The resulting tool, called CUBETESTERAI, includes a user-friendly web interface and the integration of a CI/CD pipeline using GitLab and Docker. These components streamline the automated test generation process, allowing developers to generate JUnit tests directly from their code snippets with minimal manual intervention. The final implementation executes the LLaMA models through RunPod, an online GPU service, which also enhances the privacy of our tool. Using the advanced natural language processing capabilities of the LLaMA model, CUBETESTERAI is able to generate test cases that provide high code coverage and accurate validation of software functionalities in Java-based Spring Boot applications. Furthermore, it efficiently manages resource-intensive operations and refines the generated tests to address common issues like missing imports and handling of private methods. By comparing CUBETESTERAI with some state-of-the-art tools, we show that our proposal consistently demonstrates competitive and, in many cases, better performance in terms of code coverage in different real-life Java programs.