arXiv Computer Science @arxiv_cs@qoto.org

Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniDepth-Occ. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras, and the data volume has reached twice that of SemanticKITTI. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance.

Human intention detection with hand motion prediction is critical to drive the upper-extremity assistive robots in neurorehabilitation applications. However, the traditional methods relying on physiological signal measurement are restrictive and often lack environmental context. We propose a novel approach that predicts future sequences of both hand poses and joint positions. This method integrates gaze information, historical hand motion sequences, and environmental object data, adapting dynamically to the assistive needs of the patient without prior knowledge of the intended object for grasping. Specifically, we use a vector-quantized variational autoencoder for robust hand pose encoding with an autoregressive generative transformer for effective hand motion sequence prediction. We demonstrate the usability of these novel techniques in a pilot study with healthy subjects. To train and evaluate the proposed method, we collect a dataset consisting of various types of grasp actions on different objects from multiple subjects. Through extensive experiments, we demonstrate that the proposed method can successfully predict sequential hand movement. Especially, the gaze information shows significant enhancements in prediction capabilities, particularly with fewer input frames, highlighting the potential of the proposed method for real-world applications.

Implicit neural representations (INRs) have been successfully used to compress a variety of 3D surface representations such as Signed Distance Functions (SDFs), voxel grids, and also other forms of structured data such as images, videos, and audio. However, these methods have been limited in their application to unstructured data such as 3D meshes and point clouds. This work presents a simple yet effective method that extends the usage of INRs to compress 3D triangle meshes. Our method encodes a displacement field that refines the coarse version of the 3D mesh surface to be compressed using a small neural network. Once trained, the neural network weights occupy much lower memory than the displacement field or the original surface. We show that our method is capable of preserving intricate geometric textures and demonstrates state-of-the-art performance for compression ratios ranging from 4x to 380x.

This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are German receipts. We show that conventional classification metrics, represented by the F1-Score in our experiments, are insufficient for evaluating the applicability of machine learning models in practice. To address this problem, we introduce a novel metric, Document Integrity Precision (DIP), as a solution for visual document understanding and the token classification task. To the best of our knowledge, nothing comparable has been introduced in this context. DIP is a rigorous metric, describing how many documents of the test dataset require manual interventions. It enables AI researchers and software developers to conduct an in-depth investigation of the level of process automation in business software. In order to validate DIP, we conduct experiments with our created models to highlight and analyze the impact and relevance of DIP to evaluate if the model should be deployed or not in different training settings. Our results demonstrate that existing metrics barely change for isolated model impairments, whereas DIP indicates that the model requires substantial human interventions in deployment. The larger the set of entities being predicted, the less sensitive conventional metrics are, entailing poor automation quality. DIP, in contrast, remains a single value to be interpreted for entire entity sets. This highlights the importance of having metrics that focus on the business task for model training in production. Since DIP is created for the token classification task, more research is needed to find suitable metrics for other training tasks.

The rapid growth of artificial intelligence (AI) technologies has changed decision-making in many fields. But, it has also raised major privacy and ethical concerns. However, many AI incidents taxonomies and guidelines for academia, industry, and government lack grounding in real-world incidents. We analyzed 202 real-world AI privacy and ethical incidents. This produced a taxonomy that classifies incident types across AI lifecycle stages. It accounts for contextual factors such as causes, responsible entities, disclosure sources, and impacts. Our findings show insufficient incident reporting from AI developers and users. Many incidents are caused by poor organizational decisions and legal non-compliance. Only a few legal actions and corrective measures exist, while risk-mitigation efforts are limited. Our taxonomy contributes a structured approach in reporting of future AI incidents. Our findings demonstrate that current AI governance frameworks are inadequate. We urgently need child-specific protections and AI policies on social media. They must moderate and reduce the spread of harmful AI-generated content. Our research provides insights for policymakers and practitioners, which lets them design ethical AI. It also support AI incident detection and risk management. Finally, it guides AI policy development. Improved policies will protect people from harmful AI applications and support innovation in AI systems.

Since the introduction of ChatGPT in 2022, Large language models (LLMs) and Large Multimodal Models (LMM) have transformed content creation, enabling the generation of human-quality content, spanning every medium, text, images, videos, and audio. The chances offered by generative AI models are endless and are drastically reducing the time required to generate content and usually raising the quality of the generation. However, considering the complexity and the difficult traceability of the generated content, the use of these tools provides challenges in attributing AI-generated content. The difficult attribution resides for a variety of reasons, starting from the lack of a systematic fingerprinting of the generated content and ending with the enormous amount of data on which LLMs and LMM are trained, which makes it difficult to connect generated content to the training data. This scenario is raising concerns about intellectual property and ethical responsibilities. To address these concerns, in this paper, we bridge the technological, ethical, and legislative aspects, by proposing a review of the legislative and technological instruments today available and proposing a legal framework to ensure accountability. In the end, we propose three use cases of how these can be combined to guarantee that attribution is respected. However, even though the techniques available today can guarantee a greater attribution to a greater extent, strong limitations still apply, that can be solved uniquely by the development of new attribution techniques, to be applied to LLMs and LMMs.

Do robots vote? Do machines make decisions instead of us? No, (at least not yet), but this is something that could happen. The impact of Artificial Intelligence (AI) on democracy is a complex issue that requires thorough research and careful regulation. At the most important level, that of the electoral process, it is noted that it is not determined by the AI, but it is greatly impacted by its multiple applications. New types of online campaigns, driven by AI applications, are replacing traditional ones. The potential for manipulating voters and indirectly influencing the electoral outcome should not be underestimated. Certainly, instances of voter manipulation are not absent from traditional political campaigns, with the only difference being that digital manipulation is often carried out without our knowledge, e.g. by monitoring our behavior on social media. Nevertheless, we should not overlook the positive impact that AI has in the upgrading of democratic institutions by providing a forum for participation in decision-making. In this context, as a first step, we look into the potential jeopardization of democratic processes posed by the use of AI tools. Secondly, we consider the possibility of strengthening democratic processes by using AI, as well as the democratization of AI itself through the possibilities it offers. And thirdly, the impact of AI on the representative system is also discussed. The paper is concluded with recommendations and conclusions.

Due to increased computing use, data centers consume and emit a lot of energy and carbon. These contributions are expected to rise as big data analytics, digitization, and large AI models grow and become major components of daily working routines. To reduce the environmental impact of software development, green (sustainable) coding and claims that AI models can improve energy efficiency have grown in popularity. Furthermore, in the automotive industry, where software increasingly governs vehicle performance, safety, and user experience, the principles of green coding and AI-driven efficiency could significantly contribute to reducing the sector's environmental footprint. We present an overview of green coding and metrics to measure AI model sustainability awareness. This study introduces LLM as a service and uses a generative commercial AI language model, GitHub Copilot, to auto-generate code. Using sustainability metrics to quantify these AI models' sustainability awareness, we define the code's embodied and operational carbon.

The integration of Large Language Models (LLMs) into social science research presents transformative opportunities for advancing scientific inquiry, particularly in public administration (PA). However, the absence of standardized methodologies for using LLMs poses significant challenges for ensuring transparency, reproducibility, and replicability. This manuscript introduces the TaMPER framework-a structured methodology organized around five critical decision points: Task, Model, Prompt, Evaluation, and Reporting. The TaMPER framework provides scholars with a systematic approach to leveraging LLMs effectively while addressing key challenges such as model variability, prompt design, evaluation protocols, and transparent reporting practices.

This short paper puts forward a vision for a new democratic model enabled by the recent technological advances in agentic AI. It therefore opens with drawing a clear and concise picture of the model, and only later addresses related proposals and research directions, and concerns regarding feasibility and safety. It ends with a note on the timeliness of this idea and on optimism. The model proposed is that of assigning each citizen an AI Agent that would serve as their political delegate, enabling the return to direct democracy. The paper examines this models relation to existing research, its potential setbacks and feasibility and argues for its further development.

Histograms provide a powerful means of summarizing large data sets by representing their distribution in a compact, binned form. The HistogramTools R package enhances R built-in histogram functionality, offering advanced methods for manipulating and analyzing histograms, especially in large-scale data environments. Key features include the ability to serialize histograms using Protocol Buffers for distributed computing tasks, tools for merging and modifying histograms, and techniques for measuring and visualizing information loss in histogram representations. The package is particularly suited for environments utilizing MapReduce, where efficient storage and data sharing are critical. This paper presents various methods of histogram bin manipulation, distance measures, quantile approximation, and error estimation in cumulative distribution functions (CDFs) derived from histograms. Visualization techniques and efficient storage representations are also discussed alongside applications for large data processing and distributed computing tasks.

Recent advancements in large language models (LLMs) have prompted interest in deploying these models on mobile devices to enable new applications without relying on cloud connectivity. However, the efficiency constraints of deploying LLMs on resource-limited devices present significant challenges. In this paper, we conduct a comprehensive measurement study to evaluate the efficiency tradeoffs between mobile-based, edge-based, and cloud-based deployments for LLM applications. We implement AutoLife-Lite, a simplified LLM-based application that analyzes smartphone sensor data to infer user location and activity contexts. Our experiments reveal that: (1) Only small-size LLMs (<4B parameters) can run successfully on powerful mobile devices, though they exhibit quality limitations compared to larger models; (2) Model compression is effective in lower the hardware requirement, but may lead to significant performance degradation; (3) The latency to run LLMs on mobile devices with meaningful output is significant (>30 seconds), while cloud services demonstrate better time efficiency (<10 seconds); (4) Edge deployments offer intermediate tradeoffs between latency and model capabilities, with different results on CPU-based and GPU-based settings. These findings provide valuable insights for system designers on the current limitations and future directions for on-device LLM applications.

We propose a tensor generalized approximate message passing (TeG-AMP) algorithm for low-rank tensor inference, which can be used to solve tensor completion and decomposition problems. We derive TeG-AMP algorithm as an approximation of the sum-product belief propagation algorithm in high dimensions where the central limit theorem and Taylor series approximations are applicable. As TeG-AMP is developed based on a general TR decomposition model, it can be directly applied to many low-rank tensor types. Moreover, our TeG-AMP can be simplified based on the CP decomposition model and a tensor simplified AMP is proposed for low CP-rank tensor inference problems. Experimental results demonstrate that the proposed methods significantly improve recovery performances since it takes full advantage of tensor structures.

Text-to-image generation (T2I) has become a key area of research with broad applications. However, existing methods often struggle with complex spatial relationships and fine-grained control over multiple concepts. Many existing approaches require significant architectural modifications, extensive training, or expert-level prompt engineering. To address these challenges, we introduce \textbf{LayerCraft}, an automated framework that leverages large language models (LLMs) as autonomous agents for structured procedural generation. LayerCraft enables users to customize objects within an image and supports narrative-driven creation with minimal effort. At its core, the system includes a coordinator agent that directs the process, along with two specialized agents: \textbf{ChainArchitect}, which employs chain-of-thought (CoT) reasoning to generate a dependency-aware 3D layout for precise instance-level control, and the \textbf{Object-Integration Network (OIN)}, which utilizes LoRA fine-tuning on pre-trained T2I models to seamlessly blend objects into specified regions of an image based on textual prompts without requiring architectural changes. Extensive evaluations demonstrate LayerCraft's versatility in applications ranging from multi-concept customization to storytelling. By providing non-experts with intuitive, precise control over T2I generation, our framework democratizes creative image creation. Our code will be released upon acceptance at github.com/PeterYYZhang/LayerCraft

Organisations are rapidly adopting artificial intelligence (AI) tools to perform tasks previously undertaken by people. The potential benefits are enormous. Separately, some organisations deploy personnel security measures to mitigate the security risks arising from trusted human insiders. Unfortunately, there is no meaningful interplay between the rapidly evolving domain of AI and the traditional world of personnel security. This is a problem. The complex risks from human insiders are hard enough to understand and manage, despite many decades of effort. The emerging security risks from AI insiders are even more opaque. Both sides need all the help they can get. Some of the concepts and approaches that have proved useful in dealing with human insiders are also applicable to the emerging risks from AI insiders. Furthermore, AI can be used defensively to protect against both human and AI insiders.

We address the challenge of product configuration in the context of increasing customer demand for diverse and complex products. We propose a solution through a curated selection of product model benchmarks formulated in the COOM language, divided into three fragments of increasing complexity. Each fragment is accompanied by a corresponding bike model example, and additional scalable product models are included in the COOM suite, along with relevant resources. We outline an ASP-based workflow for solving COOM-based configuration problems, highlighting its adaptability to different paradigms and alternative ASP solutions. The COOM Suite aims to provide a comprehensive, accessible, and representative set of examples that can serve as a common ground for stakeholders in the field of product configuration.

Integrating large language models (LLMs) like DeepSeek R1 into healthcare requires rigorous evaluation of their reasoning alignment with clinical expertise. This study assesses DeepSeek R1's medical reasoning against expert patterns using 100 MedQA clinical cases. The model achieved 93% diagnostic accuracy, demonstrating systematic clinical judgment through differential diagnosis, guideline-based treatment selection, and integration of patient-specific factors. However, error analysis of seven incorrect cases revealed persistent limitations: anchoring bias, challenges reconciling conflicting data, insufficient exploration of alternatives, overthinking, knowledge gaps, and premature prioritization of definitive treatment over intermediate care. Crucially, reasoning length correlated with accuracy - shorter responses (<5,000 characters) were more reliable, suggesting extended explanations may signal uncertainty or rationalization of errors. While DeepSeek R1 exhibits foundational clinical reasoning capabilities, recurring flaws highlight critical areas for refinement, including bias mitigation, knowledge updates, and structured reasoning frameworks. These findings underscore LLMs' potential to augment medical decision-making through artificial reasoning but emphasize the need for domain-specific validation, interpretability safeguards, and confidence metrics (e.g., response length thresholds) to ensure reliability in real-world applications.

Vision-based tactile sensors use structured light to measure deformation in their elastomeric interface. Until now, vision-based tactile sensors such as DIGIT and GelSight have been using a single, static pattern of structured light tuned to the specific form factor of the sensor. In this work, we investigate the effectiveness of dynamic illumination patterns, in conjunction with image fusion techniques, to improve the quality of sensing of vision-based tactile sensors. Specifically, we propose to capture multiple measurements, each with a different illumination pattern, and then fuse them together to obtain a single, higher-quality measurement. Experimental results demonstrate that this type of dynamic illumination yields significant improvements in image contrast, sharpness, and background difference. This discovery opens the possibility of retroactively improving the sensing quality of existing vision-based tactile sensors with a simple software update, and for new hardware designs capable of fully exploiting dynamic illumination.

While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code. Testing LLM-generated code therefore poses significant risks to assessment infrastructure tasked with executing untrusted code. To address these risks, this work focuses on evaluating the security and confidentiality properties of test environments, reducing the risk that LLM-generated code may compromise the assessment infrastructure. We introduce SandboxEval, a test suite featuring manually crafted test cases that simulate real-world safety scenarios for LLM assessment environments in the context of untrusted code execution. The suite evaluates vulnerabilities to sensitive information exposure, filesystem manipulation, external communication, and other potentially dangerous operations in the course of assessment activity. We demonstrate the utility of SandboxEval by deploying it on an open-source implementation of Dyff, an established AI assessment framework used to evaluate the safety of LLMs at scale. We show, first, that the test suite accurately describes limitations placed on an LLM operating under instructions to generate malicious code. Second, we show that the test results provide valuable insights for developers seeking to harden assessment infrastructure and identify risks associated with LLM execution activities.

Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing and filtering strategies. In particular, research exploring modifications to Code-LMs' pre-training objectives, geared towards improving data efficiency and better disentangling between syntax and semantics, has been noticeably sparse, especially compared with corresponding efforts in natural language LMs. In this work, we examine grounding on obfuscated code as a means of helping Code-LMs look beyond the surface-form syntax and enhance their pre-training sample efficiency. To this end, we compile ObscuraX, a dataset of approximately 55M source and obfuscated code pairs in seven languages. Subsequently, we pre-train ObscuraCoder models, ranging in size from 255M to 2.8B parameters, on a 272B-token corpus that includes ObscuraX and demonstrate that our obfuscation-based pre-training recipe leads to consistent improvements in Code-LMs' abilities compared to both vanilla autoregressive pre-training as well as existing de-obfuscation (DOBF) objectives. ObscuraCoder demonstrates sizeable gains across multiple tests of syntactic and semantic code understanding, along with improved capabilities in multilingual code completion, multilingual code commit summarization, and multi-purpose library-oriented code generation.