arXiv Computer Science @arxiv_cs@qoto.org

With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning. However, existing research has primarily focused on text-based algebra problems, neglecting the study of geometry due to the lack of high-quality geometric datasets. To address this gap, this paper introduces AutoGeo, a novel approach for automatically generating mathematical geometric images to fulfill the demand for large-scale and diverse geometric datasets. AutoGeo facilitates the creation of AutoGeo-100k, an extensive repository comprising 100k high-quality geometry image-text pairs. By leveraging precisely defined geometric clauses, AutoGeo-100k contains a wide variety of geometric shapes, including lines, polygons, circles, and complex spatial relationships, etc. Furthermore, this paper demonstrates the efficacy of AutoGeo-100k in enhancing the performance of multimodal large language models through fine-tuning. Experimental results indicate significant improvements in the model's ability in handling geometric images, as evidenced by enhanced accuracy in tasks such as geometric captioning and mathematical reasoning. This research not only fills a critical gap in the availability of geometric datasets but also paves the way for the advancement of sophisticated AI-driven tools in education and research. Project page: https://autogeo-official.github.io/.

Large Language Models (LLMs), capable of handling multi-modal input and outputs such as text, voice, images, and video, are transforming the way we process information. Beyond just generating textual responses to prompts, they can integrate with different software platforms to offer comprehensive solutions across diverse applications. In this paper, we present ChatSUMO, a LLM-based agent that integrates language processing skills to generate abstract and real-world simulation scenarios in the widely-used traffic simulator - Simulation of Urban MObility (SUMO). Our methodology begins by leveraging the LLM for user input which converts to relevant keywords needed to run python scripts. These scripts are designed to convert specified regions into coordinates, fetch data from OpenStreetMap, transform it into a road network, and subsequently run SUMO simulations with the designated traffic conditions. The outputs of the simulations are then interpreted by the LLM resulting in informative comparisons and summaries. Users can continue the interaction and generate a variety of customized scenarios without prior traffic simulation expertise. For simulation generation, we created a real-world simulation for the city of Albany with an accuracy of 96\%. ChatSUMO also realizes the customizing of edge edit, traffic light optimization, and vehicle edit by users effectively.

As foundation models have accumulated hundreds of millions of users, developers have begun to take steps to prevent harmful types of uses. One salient intervention that foundation model developers adopt is acceptable use policies: legally binding policies that prohibit users from using a model for specific purposes. This paper identifies acceptable use policies from 30 foundation model developers, analyzes the use restrictions they contain, and argues that acceptable use policies are an important lens for understanding the regulation of foundation models. Taken together, developers' acceptable use policies include 127 distinct use restrictions; the wide variety in the number and type of use restrictions may create fragmentation across the AI supply chain. Developers also employ acceptable use policies to prevent competitors or specific industries from making use of their models. Developers alone decide what constitutes acceptable use, and rarely provide transparency about how they enforce their policies. In practice, acceptable use policies are difficult to enforce, and scrupulous enforcement can act as a barrier to researcher access and limit beneficial uses of foundation models. Nevertheless, acceptable use policies for foundation models are an early example of self-regulation that have a significant impact on the market for foundation models and the overall AI ecosystem.

Cooperative perception, offering a wider field of view than standalone perception, is becoming increasingly crucial in autonomous driving. This perception is enabled through vehicle-to-vehicle (V2V) communication, allowing connected automated vehicles (CAVs) to exchange sensor data, such as light detection and ranging (LiDAR) point clouds, thereby enhancing the collective understanding of the environment. In this paper, we leverage an importance map to distill critical semantic information, introducing a cooperative perception semantic communication framework that employs intermediate fusion. To counter the challenges posed by time-varying multipath fading, our approach incorporates the use of orthogonal frequency-division multiplexing (OFDM) along with channel estimation and equalization strategies. Furthermore, recognizing the necessity for reliable transmission, especially in the low SNR scenarios, we introduce a novel semantic error detection method that is integrated with our semantic communication framework in the spirit of hybrid automatic repeated request (HARQ). Simulation results show that our model surpasses the traditional separate source-channel coding methods in perception performance, both with and without HARQ. Additionally, in terms of throughput, our proposed HARQ schemes demonstrate superior efficiency to the conventional coding approaches.

We conducted a reproducibility study on Integrated Gradients (IG) based methods and the Important Direction Gradient Integration (IDGI) framework. IDGI eliminates the explanation noise in each step of the computation of IG-based methods that use the Riemann Integration for integrated gradient computation. We perform a rigorous theoretical analysis of IDGI and raise a few critical questions that we later address through our study. We also experimentally verify the authors' claims concerning the performance of IDGI over IG-based methods. Additionally, we varied the number of steps used in the Riemann approximation, an essential parameter in all IG methods, and analyzed the corresponding change in results. We also studied the numerical instability of the attribution methods to check the consistency of the saliency maps produced. We developed the complete code to implement IDGI over the baseline IG methods and evaluated them using three metrics since the available code was insufficient for this study.

Deploying Deep Learning (DL) on embedded end devices is a scorching trend in pervasive computing. Since most Microcontrollers on embedded devices have limited computing power, it is necessary to add a DL accelerator. Embedded Field Programmable Gate Arrays (FPGAs) are suitable for deploying DL accelerators for embedded devices, but developing an energy-efficient DL accelerator on an FPGA is not easy. Therefore, we propose the ElasticAI-Workflow that aims to help DL developers to create and deploy DL models as hardware accelerators on embedded FPGAs. This workflow consists of two key components: the ElasticAI-Creator and the Elastic Node. The former is a toolchain for automatically generating DL accelerators on FPGAs. The latter is a hardware platform for verifying the performance of the generated accelerators. With this combination, the performance of the accelerator can be sufficiently guaranteed. We will demonstrate the potential of our approach through a case study.

"Synthetic samples" based on large language models (LLMs) have been argued to serve as efficient alternatives to surveys of humans, assuming that their training data includes information on human attitudes and behavior. However, LLM-synthetic samples might exhibit bias, for example due to training data and fine-tuning processes being unrepresentative of diverse contexts. Such biases risk reinforcing existing biases in research, policymaking, and society. Therefore, researchers need to investigate if and under which conditions LLM-generated synthetic samples can be used for public opinion prediction. In this study, we examine to what extent LLM-based predictions of individual public opinion exhibit context-dependent biases by predicting the results of the 2024 European Parliament elections. Prompting three LLMs with individual-level background information of 26,000 eligible European voters, we ask the LLMs to predict each person's voting behavior. By comparing them to the actual results, we show that LLM-based predictions of future voting behavior largely fail, their accuracy is unequally distributed across national and linguistic contexts, and they require detailed attitudinal information in the prompt. The findings emphasize the limited applicability of LLM-synthetic samples to public opinion prediction. In investigating their contextual biases, this study contributes to the understanding and mitigation of inequalities in the development of LLMs and their applications in computational social science.

Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. Retrieval-Augmented Generation (RAG) systems address these issues by incorporating external knowledge, but suffer from retrieval errors, ineffective context integration, and high operational costs. This paper presents the Hybrid Parameter-Adaptive RAG (HyPA-RAG) system, designed for the AI legal domain, with NYC Local Law 144 (LL144) as the test case. HyPA-RAG integrates a query complexity classifier for adaptive parameter tuning, a hybrid retrieval approach combining dense, sparse, and knowledge graph methods, and a comprehensive evaluation framework with tailored question types and metrics. Testing on LL144 demonstrates that HyPA-RAG enhances retrieval accuracy, response fidelity, and contextual precision, offering a robust and adaptable solution for high-stakes legal and policy applications.

In this paper, we study how generative AI and specifically large language models (LLMs) impact learning in coding classes. We show across three studies that LLM usage can have positive and negative effects on learning outcomes. Using observational data from university-level programming courses, we establish such effects in the field. We replicate these findings in subsequent experimental studies, which closely resemble typical learning scenarios, to show causality. We find evidence for two contrasting mechanisms that determine the overall effect of LLM usage on learning. Students who use LLMs as personal tutors by conversing about the topic and asking for explanations benefit from usage. However, learning is impaired for students who excessively rely on LLMs to solve practice exercises for them and thus do not invest sufficient own mental effort. Those who never used LLMs before are particularly prone to such adverse behavior. Students without prior domain knowledge gain more from having access to LLMs. Finally, we show that the self-perceived benefits of using LLMs for learning exceed the actual benefits, potentially resulting in an overestimation of one's own abilities. Overall, our findings show promising potential of LLMs as learning support, however also that students have to be very cautious of possible pitfalls.

This study explores the performance of large language models (LLMs) in solving competitive programming problems from the Romanian Informatics Olympiad at the county level. Romania, a leading nation in computer science competitions, provides an ideal environment for evaluating LLM capabilities due to its rich history and stringent competition standards. We collected and analyzed a dataset comprising 304 challenges from 2002 to 2023, focusing on solutions written by LLMs in C++ and Python for these problems. Our primary goal is to understand why LLMs perform well or poorly on different tasks. We evaluated various models, including closed-source models like GPT-4 and open-weight models such as CodeLlama and RoMistral, using a standardized process involving multiple attempts and feedback rounds. The analysis revealed significant variations in LLM performance across different grades and problem types. Notably, GPT-4 showed strong performance, indicating its potential use as an educational tool for middle school students. We also observed differences in code quality and style across various LLMs

Effective activation functions introduce non-linear transformations, providing neural networks with stronger fitting capa-bilities, which help them better adapt to real data distributions. Huawei Noah's Lab believes that dynamic activation functions are more suitable than static activation functions for enhancing the non-linear capabilities of neural networks. Tsinghua University's related research also suggests using dynamically adjusted activation functions. Building on the ideas of using fine-tuned activation functions from Tsinghua University and Huawei Noah's Lab, we propose a series-based learnable ac-tivation function called LSLU (Learnable Series Linear Units). This method simplifies deep learning networks while im-proving accuracy. This method introduces learnable parameters θ and ω to control the activation function, adapting it to the current layer's training stage and improving the model's generalization. The principle is to increase non-linearity in each activation layer, boosting the network's overall non-linearity. We evaluate LSLU's performance on CIFAR10, CIFAR100, and specific task datasets (e.g., Silkworm), validating its effectiveness. The convergence behavior of the learnable parameters θ and ω, as well as their effects on generalization, are analyzed. Our empirical results show that LSLU enhances the general-ization ability of the original model in various tasks while speeding up training. In VanillaNet training, parameter θ initially decreases, then increases before stabilizing, while ω shows an opposite trend. Ultimately, LSLU achieves a 3.17% accuracy improvement on CIFAR100 for VanillaNet (Table 3). Codes are available at https://github.com/vontran2021/Learnable-series-linear-units-LSLU.

Learning about databases is indispensable for individuals studying software engineering or computer science or those involved in the IT industry. We analyzed a remote educational escape room for teaching about databases in four different higher education courses in two consecutive academic years. We employed three instruments for evaluation: a pre- and post-test to assess the escape room's effectiveness for student learning, a questionnaire to gather students' perceptions, and a Web platform that unobtrusively records students' interactions and performance. We show novel evidence that educational escape rooms conducted remotely can be engaging as well as effective for teaching about databases.

Integrating experimental data into simulations is crucial for predicting material behaviour, especially in fracture mechanics. Digital Image Correlation (DIC) provides precise displacement measurements, essential for evaluating strain energy release rates and stress intensity factors (SIF) around cracks. Translating DIC data into CAE software like ABAQUS has been challenging. DIC2CAE, a MATLAB-based tool, automates this conversion, enabling accurate simulations. It uses the J-integral method to calculate SIFs and handles complex scenarios without needing specimen geometry or applied loads. DIC2CAE enhances fracture mechanics simulations' reliability, accelerating materials research and development.

As is widely known, the computational speed and power consumption are two critical parameters in microprocessor design. A solution for these issues is the application specific instruction set processor (ASIP) methodology, which can improve speed and reduce power consumption of the general purpose processor (GPP) technique. In ASIP, changing the instruction set architecture (ISA) of the processor will lead to alter the number and the mean time of accesses to the cache memory. This issue has a direct impact on the processor energy consumption. In this work, we study the impacts of extended ISA on the energy consumption of the extended ISA processor. Also, we demonstrate the extended ISA let the designer to reduce the cache size in order to minimize the energy consumption while meeting performance constraint.

Spiking neural networks (SNNs) are generally regarded as more energy-efficient because they do not use multiplications. However, most SNN works only consider the counting of additions to evaluate energy consumption, neglecting other overheads such as memory accesses and data movement operations. This oversight can lead to a misleading perception of efficiency, especially when state-of-the-art SNN accelerators operate with very small time window sizes. In this paper, we present a detailed comparison of the energy consumption of artificial neural networks (ANNs) and SNNs from a hardware perspective. We provide accurate formulas for energy consumption based on classical multi-level memory hierarchy architectures, commonly used neuromorphic dataflow architectures, and our proposed improved spatial-dataflow architecture. Our research demonstrates that to achieve comparable accuracy and greater energy efficiency than ANNs, SNNs require strict limitations on both time window size T and sparsity s. For instance, with the VGG16 model and a fixed T of 6, the neuron sparsity rate must exceed 93% to ensure energy efficiency across most architectures. Inspired by our findings, we explore strategies to enhance energy efficiency by increasing sparsity. We introduce two regularization terms during training that constrain weights and activations, effectively boosting the sparsity rate. Our experiments on the CIFAR-10 dataset, using T of 6, show that our SNNs consume 69% of the energy used by optimized ANNs on spatial-dataflow architectures, while maintaining an SNN accuracy of 94.18%. This framework, developed using PyTorch, is publicly available for use and further research.

Scale-free networks are ubiquitous in social, biological and technological networked systems. Dynamic Scale-free networks and their synchronizations are important to understand and predict the behavior of social, biological and technological networked systems. In this research, computational experiments have been conducted to understand the sustainability of scale-free properties during the time of synchronizations in dynamic scale-free networks. Two synchronization phenomena which are synchronization based on states of nodes with coupling configuration matrix and synchronization based on states of nodes with network centralities have been implemented for the synchronization in dynamic scale-free networks. In experiments, dynamic scale-free networks have been generated with a network generation algorithm and analyzed to understand the fluctuation from the scale-free properties in their phases during the time of synchronizations.

Safety is one of the fundamental challenges in control theory. Recently, multi-step optimal control problems for discrete-time dynamical systems were developed to ensure stability, while adhering to input constraints and safety-critical requirements. This was achieved by incorporating discrete-time Control Barrier Functions (CBFs) within a Model Predictive Control (MPC) framework. Existing work usually centers on the feasibility or safety of optimization problems when the boundaries of safe sets are clearly defined. Most of this research limits discussions to CBFs with relative degree one with respect to the system dynamics. Furthermore, real-time computation becomes challenging in MPC problems with large horizons. In this paper, we introduce a framework that addresses the safety-critical MPC problem through iterative optimization, applicable across CBFs of any relative degree. Our approach involves linearizing the nonlinear system dynamics and safety constraints, modeled as Discrete-time High-Order CBFs (DHOCBFs), at each time step. Additionally, when the boundaries of the safe sets are complex, we present a learning-based method to develop linear boundary equations for these safe sets. These equations are then converted into linearized DHOCBFs. The benefits of computational performance and safe avoidance of obstacles with diverse shapes are examined and confirmed through numerical results.

In this paper we consider the problem of releasing a Gaussian Differentially Private (GDP) 3D human face. The human face is a complex structure with many features and inherently tied to one's identity. Protecting this data, in a formally private way, is important yet challenging given the dimensionality of the problem. We extend approximate DP techniques for functional data to the GDP framework. We further propose a novel representation, face radial curves, of a 3D face as a set of functions and then utilize our proposed GDP functional data mechanism. To preserve the shape of the face while injecting noise we rely on tools from shape analysis for our novel representation of the face. We show that our method preserves the shape of the average face and injects less noise than traditional methods for the same privacy budget. Our mechanism consists of two primary components, the first is generally applicable to function value summaries (as are commonly found in nonparametric statistics or functional data analysis) while the second is general to disk-like surfaces and hence more applicable than just to human faces.

Adversarial actions and a rapid climate change are disrupting operations of infrastructure networks (e.g., energy, water, and transportation systems). Unaddressed disruptions lead to system-wide shutdowns, emphasizing the need for quick and robust identification methods. One significant disruption arises from edge changes (addition or deletion) in networks. We present an $\ell_1$-norm regularized least-squares framework to identify multiple but sparse edge changes using noisy data. We focus only on networks that obey equilibrium equations, as commonly observed in the above sectors. The presence or lack of edges in these networks is captured by the sparsity pattern of the weighted, symmetric Laplacian matrix, while noisy data are node injections and potentials. Our proposed framework systematically leverages the inherent structure within the Laplacian matrix, effectively avoiding overparameterization. We demonstrate the robustness and efficacy of the proposed approach through a series of representative examples, with a primary emphasis on power networks.

Russian Internet Trolls use fake personas to spread disinformation through multiple social media streams. Given the increased frequency of this threat across social media platforms, understanding those operations is paramount in combating their influence. Using Twitter content identified as part of the Russian influence network, we created a predictive model to map the network operations. We classify accounts type based on their authenticity function for a sub-sample of accounts by introducing logical categories and training a predictive model to identify similar behavior patterns across the network. Our model attains 88% prediction accuracy for the test set. Validation is done by comparing the similarities with the 3 million Russian troll tweets dataset. The result indicates a 90.7% similarity between the two datasets. Furthermore, we compare our model predictions on a Russian tweets dataset, and the results state that there is 90.5% correspondence between the predictions and the actual categories. The prediction and validation results suggest that our predictive model can assist with mapping the actors in such networks.