Search

A major challenge with palm vein images is that slight movements of the fingers and thumb, or variations in hand posture, can stretch the skin in different areas and alter the vein patterns. This can result in an infinite number of variations in palm vein images for a given individual. This paper introduces a novel filtering technique for SIFT-based feature matching, known as the Mean and Median Distance (MMD) Filter. This method evaluates the differences in keypoint coordinates and computes the mean and median in each direction to eliminate incorrect matches. Experiments conducted on the 850nm subset of the CASIA dataset indicate that the proposed MMD filter effectively preserves correct points while reducing false positives detected by other filtering methods. A comparison with existing SIFT-based palm vein recognition systems demonstrates that the proposed MMD filter delivers outstanding performance, achieving lower Equal Error Rate (EER) values. This article presents an extended author's version based on our previous work, A Keypoint Filtering Method for SIFT based Palm-Vein Recognition., Comment: Our previous work, presented at the 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) and published in IEEE Xplore. The code for the MMD filter is available at https://github.com/kaveenperera/MMD_filter under Mozilla Public License Version 2.0

This article presents an extended author's version based on our previous work, where we introduced the Multiple Overlapping Tiles (MOT) method for palm vein image enhancement. To better reflect the specific operations involved, we rename MOT to ILACS-LGOT (Intensity-Limited Adaptive Contrast Stretching with Layered Gaussian-weighted Overlapping Tiles). This revised terminology more accurately represents the method's approach to contrast enhancement and blocky effect mitigation. Additionally, this article provides a more detailed analysis, including expanded evaluations, graphical representations, and sample-based comparisons, demonstrating the effectiveness of ILACS-LGOT over existing methods., Comment: Our previous work, A Keypoint Filtering Method for SIFT based Palm-Vein Recognition, presented at the 2022 CoDIT and published in IEEE Xplore (DOI: 10.1109/CoDIT55151.2022.9804034). The code for the ILACS-LGOT method is available at: https://github.com/kaveenperera/ILACS-Enhancement under Mozilla Public License Version 2.0

The rapid advancement of Artificial Intelligence (AI) technology is profoundly transforming human society and concurrently presenting a series of ethical, legal, and social issues. The effective governance of AI has become a crucial global concern. Since 2022, the extensive deployment of generative AI, particularly large language models, marked a new phase in AI governance. Continuous efforts are being made by the international community in actively addressing the novel challenges posed by these AI developments. As consensus on international governance continues to be established and put into action, the practical importance of conducting a global assessment of the state of AI governance is progressively coming to light. In this context, we initiated the development of the AI Governance InternationaL Evaluation Index (AGILE Index). Adhering to the design principle, "the level of governance should match the level of development," the inaugural evaluation of the AGILE Index commences with an exploration of four foundational pillars: the development level of AI, the AI governance environment, the AI governance instruments, and the AI governance effectiveness. It covers 39 indicators across 18 dimensions to comprehensively assess the AI governance level of 14 representative countries globally. The index is utilized to delve into the status of AI governance to date in 14 countries for the first batch of evaluation. The aim is to depict the current state of AI governance in these countries through data scoring, assist them in identifying their governance stage and uncovering governance issues, and ultimately offer insights for the enhancement of their AI governance systems., Comment: Evaluation Report. 85 pages, 30 Figures

Binary Spiking Neural Networks (BSNNs) inherit the eventdriven paradigm of SNNs, while also adopting the reduced storage burden of binarization techniques. These distinct advantages grant BSNNs lightweight and energy-efficient characteristics, rendering them ideal for deployment on resource-constrained edge devices. However, due to the binary synaptic weights and non-differentiable spike function, effectively training BSNNs remains an open question. In this paper, we conduct an in-depth analysis of the challenge for BSNN learning, namely the frequent weight sign flipping problem. To mitigate this issue, we propose an Adaptive Gradient Modulation Mechanism (AGMM), which is designed to reduce the frequency of weight sign flipping by adaptively adjusting the gradients during the learning process. The proposed AGMM can enable BSNNs to achieve faster convergence speed and higher accuracy, effectively narrowing the gap between BSNNs and their full-precision equivalents. We validate AGMM on both static and neuromorphic datasets, and results indicate that it achieves state-of-the-art results among BSNNs. This work substantially reduces storage demands and enhances SNNs' inherent energy efficiency, making them highly feasible for resource-constrained environments., Comment: 9 pages, 8 figures, AAAI conference

The combination of Spiking Neural Networks (SNNs) and Vision Transformers (ViTs) holds potential for achieving both energy efficiency and high performance, particularly suitable for edge vision applications. However, a significant performance gap still exists between SNN-based ViTs and their ANN counterparts. Here, we first analyze why SNN-based ViTs suffer from limited performance and identify a mismatch between the vanilla self-attention mechanism and spatio-temporal spike trains. This mismatch results in degraded spatial relevance and limited temporal interactions. To address these issues, we draw inspiration from biological saccadic attention mechanisms and introduce an innovative Saccadic Spike Self-Attention (SSSA) method. Specifically, in the spatial domain, SSSA employs a novel spike distribution-based method to effectively assess the relevance between Query and Key pairs in SNN-based ViTs. Temporally, SSSA employs a saccadic interaction module that dynamically focuses on selected visual areas at each timestep and significantly enhances whole scene understanding through temporal interactions. Building on the SSSA mechanism, we develop a SNN-based Vision Transformer (SNN-ViT). Extensive experiments across various visual tasks demonstrate that SNN-ViT achieves state-of-the-art performance with linear computational complexity. The effectiveness and efficiency of the SNN-ViT highlight its potential for power-critical edge vision applications., Comment: Published as a conference paper at ICLR 2025

Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We propose AQ-Net, a spatiotemporal reanalysis model for both observed and unobserved stations in the near future. AQ-Net utilizes the LSTM and multi-head attention for the temporal regression. We also propose a cyclic encoding technique to ensure continuous time representation. To learn fine-grained spatial air quality estimation, we incorporate AQ-Net with the neural kNN to explore feature-based interpolation, such that we can fill the spatial gaps given coarse observation stations. To demonstrate the efficiency of our model for spatiotemporal reanalysis, we use data from 2013-2017 collected in northern China for PM2.5 analysis. Extensive experiments show that AQ-Net excels in air quality reanalysis, highlighting the potential of hybrid spatio-temporal models to better capture environmental dynamics, especially in urban areas where both spatial and temporal variability are critical.

Brain-inspired Spiking Neural Networks (SNNs) leverage sparse spikes to encode information and operate in an asynchronous event-driven manner, offering a highly energy-efficient paradigm for machine intelligence. However, the current SNN community focuses primarily on performance improvement by developing large-scale models, which limits the applicability of SNNs in resource-limited edge devices. In this paper, we propose a hardware-friendly and lightweight SNN, aimed at effectively deploying high-performance SNN in resource-limited scenarios. Specifically, we first develop a baseline model that integrates uniform quantization and structured pruning, called QP-SNN baseline. While this baseline significantly reduces storage demands and computational costs, it suffers from performance decline. To address this, we conduct an in-depth analysis of the challenges in quantization and pruning that lead to performance degradation and propose solutions to enhance the baseline's performance. For weight quantization, we propose a weight rescaling strategy that utilizes bit width more effectively to enhance the model's representation capability. For structured pruning, we propose a novel pruning criterion using the singular value of spatiotemporal spike activities to enable more accurate removal of redundant kernels. Extensive experiments demonstrate that integrating two proposed methods into the baseline allows QP-SNN to achieve state-of-the-art performance and efficiency, underscoring its potential for enhancing SNN deployment in edge intelligence computing., Comment: 26 pages, 17 figures, Published as a conference paper at ICLR 2025

Fractional quantum Hall (FQH) systems are strongly interacting electron systems with topological order. These systems are characterized by novel ground states, fractionally charged and neutral excitations. The neutral excitations are dominated by a low-energy collective magnetoroton mode. Here we derive and use a quasi-one-dimensional model to investigate the ultrafast nonequilibrium dynamics of a laser-driven FQH system within a two-Landau-level approximation. As opposed to the traditional and synthetic bilayers, our model accounts for interactions where electrons can scatter from one Landau-level to another. By performing exact time evolution of the system, we create an out-of-equilibrium state following the laser pulse that shows rich physics. Our calculations show the presence of non-trivial excited modes. One of these modes is electromagnetically active and represent density oscillations of \emph{magnetoplasmon} mode. Another mode is identified by evaluating the overlap of the initial state and the out-of-equilibrium state following the laser pulse with a quadrupole operator. This mode is analogous to the chiral-graviton mode for FQH systems recently measured in experiments [Nature {\bf 628}, 78 (2024)]. Our results show that a linearly-polarized pulse field can excite the graviton mode when inter-Landau level scattering occurs.

Language Models (LMs) have shown substantial improvements in handling factual knowledge, yet their capability to consistently represent temporal facts, which are valid only within specific timeframes, remains underexplored. To investigate this, we introduce TimeStress, a novel dataset comprising 521K statements on 2003 of the most popular temporal facts in Wikidata. Each statement contextualizes a fact with correct and incorrect dates across three precisions (Day, Month, Year). This setup allows us to evaluate LMs' ability to discern between correct and incorrect temporal statements based on their probability of being generated. We assess 18 LMs across various architectures using two metrics: the win rate, indicating how often correct dates outperform incorrect ones, and robustness, reflecting consistent performance across all dates. Our findings reveal that while some LMs achieve a win rate exceeding 80\%, robustness remains low, with the best model achieving only 6\%. Furthermore, robust knowledge at one date precision does not reliably transfer to others, highlighting a significant generalization gap. These results underscore the struggle of LMs to maintain a consistent temporal representation, supporting their limitations as reliable sources of temporal knowledge. We provide all data and code for further research., Comment: preprint v2

Even highly capable large language models (LLMs) can produce biased or unsafe responses, and alignment techniques, such as RLHF, aimed at mitigating this issue, are expensive and prone to overfitting as they retrain the LLM. This paper introduces a novel inference-time alignment approach that ensures LLMs generate safe responses almost surely, i.e., with a probability approaching one. We achieve this by framing the safe generation of inference-time responses as a constrained Markov decision process within the LLM's latent space. Crucially, we augment a safety state that tracks the evolution of safety constraints and enables us to demonstrate formal safety guarantees upon solving the MDP in the latent space. Building on this foundation, we propose InferenceGuard, a practical implementation that safely aligns LLMs without modifying the model weights. Empirically, we demonstrate InferenceGuard effectively balances safety and task performance, outperforming existing inference-time alignment methods in generating safe and aligned responses.

Inferring physical laws from data is a central challenge in science and engineering, including but not limited to healthcare, physical sciences, biosciences, social sciences, sustainability, climate, and robotics. Deep networks offer high-accuracy results but lack interpretability, prompting interest in models built from simple components. The Sparse Identification of Nonlinear Dynamics (SINDy) method has become the go-to approach for building such modular and interpretable models. SINDy leverages sparse regression with L1 regularization to identify key terms from a library of candidate functions. However, SINDy's choice of candidate library and optimization method requires significant technical expertise, limiting its widespread applicability. This work introduces Al-Khwarizmi, a novel agentic framework for physical law discovery from data, which integrates foundational models with SINDy. Leveraging LLMs, VLMs, and Retrieval-Augmented Generation (RAG), our approach automates physical law discovery, incorporating prior knowledge and iteratively refining candidate solutions via reflection. Al-Khwarizmi operates in two steps: it summarizes system observations-comprising textual descriptions, raw data, and plots-followed by a secondary step that generates candidate feature libraries and optimizer configurations to identify hidden physics laws correctly. Evaluating our algorithm on over 198 models, we demonstrate state-of-the-art performance compared to alternatives, reaching a 20 percent increase against the best-performing alternative.

This study presents a narrative review of the use of digital health technologies (DHTs) and artificial intelligence to screen and mitigate risks and mental health consequences associated with ACEs among children and youth. Several databases were searched for studies published from August 2017 to August 2022. Selected studies (1) explored the relationship between digital health interventions and mitigation of negative health outcomes associated with mental health in childhood and adolescence and (2) examined prevention of ACE occurrence associated with mental illness in childhood and adolescence. A total of 18 search papers were selected, according to our inclusion and exclusion criteria, to evaluate and identify means by which existing digital solutions may be useful in mitigating the mental health consequences associated with the occurrence of ACEs in childhood and adolescence and preventing ACE occurrence due to mental health consequences. We also highlighted a few knowledge gaps or barriers to DHT implementation and usability. Findings from the search suggest that the incorporation of DHTs, if implemented successfully, has the potential to improve the quality of related care provisions for the management of mental health consequences of adverse or traumatic events in childhood, including posttraumatic stress disorder, suicidal behavior or ideation, anxiety or depression, and attention-deficit/hyperactivity disorder. The use of DHTs, machine learning tools, natural learning processing, and artificial intelligence can positively help in mitigating ACEs and associated risk factors. Under proper legal regulations, security, privacy, and confidentiality assurances, digital technologies could also assist in promoting positive childhood experiences in children and young adults, bolstering resilience, and providing reliable public health resources to serve populations in need., Comment: 10 Pages, 1 Figure

Use of lithium as a surface coating in fusion devices improves plasma performance, but the change in wall properties affects the secondary electron emission properties of the material. Lithium oxidizes easily, which drives the emission yield well above unity. We present here simulations demonstrating the change in sheath structure from monotonic to the nonmonotonic space-charge limited sheath using an energy-dependent data-driven emission model which self-consistently captures both secondary emission and backscattering populations. Increased secondary electron emission from the material has ramifications for the degradation and erosion of the wall. Results shows that the oxidation leads to an increased electron flux into the wall, and a reduced ion flux. The net transfer of energy to the surface is significantly greater for the oxidized case than for the pure lithium case. High reflection rates of low-energy backscattered particles leads to a high re-emission rate at the wall.

Question answering systems face critical limitations in languages with limited resources and scarce data, making the development of robust models especially challenging. The Quranic QA system holds significant importance as it facilitates a deeper understanding of the Quran, a Holy text for over a billion people worldwide. However, these systems face unique challenges, including the linguistic disparity between questions written in Modern Standard Arabic and answers found in Quranic verses written in Classical Arabic, and the small size of existing datasets, which further restricts model performance. To address these challenges, we adopt a cross-language approach by (1) Dataset Augmentation: expanding and enriching the dataset through machine translation to convert Arabic questions into English, paraphrasing questions to create linguistic diversity, and retrieving answers from an English translation of the Quran to align with multilingual training requirements; and (2) Language Model Fine-Tuning: utilizing pre-trained models such as BERT-Medium, RoBERTa-Base, DeBERTa-v3-Base, ELECTRA-Large, Flan-T5, Bloom, and Falcon to address the specific requirements of Quranic QA. Experimental results demonstrate that this cross-language approach significantly improves model performance, with RoBERTa-Base achieving the highest MAP@10 (0.34) and MRR (0.52), while DeBERTa-v3-Base excels in Recall@10 (0.50) and Precision@10 (0.24). These findings underscore the effectiveness of cross-language strategies in overcoming linguistic barriers and advancing Quranic QA systems

Hallucination detection in text generation remains an ongoing struggle for natural language processing (NLP) systems, frequently resulting in unreliable outputs in applications such as machine translation and definition modeling. Existing methods struggle with data scarcity and the limitations of unlabeled datasets, as highlighted by the SHROOM shared task at SemEval-2024. In this work, we propose a novel framework to address these challenges, introducing DeepSeek Few-shot optimization to enhance weak label generation through iterative prompt engineering. We achieved high-quality annotations that considerably enhanced the performance of downstream models by restructuring data to align with instruct generative models. We further fine-tuned the Mistral-7B-Instruct-v0.3 model on these optimized annotations, enabling it to accurately detect hallucinations in resource-limited settings. Combining this fine-tuned model with ensemble learning strategies, our approach achieved 85.5% accuracy on the test set, setting a new benchmark for the SHROOM task. This study demonstrates the effectiveness of data restructuring, few-shot optimization, and fine-tuning in building scalable and robust hallucination detection frameworks for resource-constrained NLP systems.

Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased computational demands of the Transformer structure limit their practicality in resource-constrained scenarios. In this paper, we integrate binarization techniques into Transformer-based SNNs and propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer. The proposed BESTformer can significantly reduce storage and computational demands by representing weights and attention maps with a mere 1-bit. However, BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization. To address this issue, we propose a Coupled Information Enhancement (CIE) method, which consists of a reversible framework and information enhancement distillation. By maximizing the mutual information between the binary model and its full-precision counterpart, the CIE method effectively mitigates the performance degradation of the BESTformer. Extensive experiments on static and neuromorphic datasets demonstrate that our method achieves superior performance to other binary SNNs, showcasing its potential as a compact yet high-performance model for resource-limited edge devices., Comment: 11 pages, 5 figures

Web accessibility ensures that individuals with disabilities can access and interact with digital content without barriers, yet a significant majority of most used websites fail to meet accessibility standards. This study evaluates ChatGPT's (GPT-4o) ability to generate and improve web pages in line with Web Content Accessibility Guidelines (WCAG). While ChatGPT can effectively address accessibility issues when prompted, its default code often lacks compliance, reflecting limitations in its training data and prevailing inaccessible web practices. Automated and manual testing revealed strengths in resolving simple issues but challenges with complex tasks, requiring human oversight and additional iterations. Unlike prior studies, we incorporate manual evaluation, dynamic elements, and use the visual reasoning capability of ChatGPT along with the prompts to fix accessibility issues. Providing screenshots alongside prompts enhances the LLM's ability to address accessibility issues by allowing it to analyze surrounding components, such as determining appropriate contrast colors. We found that effective prompt engineering, such as providing concise, structured feedback and incorporating visual aids, significantly enhances ChatGPT's performance. These findings highlight the potential and limitations of large language models for accessible web development, offering practical guidance for developers to create more inclusive websites.

By applying the Chen-Jiang decomposition, we prove that the non-vanishing conjecture holds for an lc pair \((X, \Delta)\), where \(X\) is an irregular variety, provided it holds for lower-dimensional varieties. In the second part, we extend the Catanese-Fujita-Kawamata decomposition to the klt case \((X, \Delta)\), which leads to the existence of sections of \(K_X + \Delta\) in certain situations.

Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this alignment, given its ability to optimise models based on human feedback directly. However, the vast number of DPO variants in the literature has made it increasingly difficult for researchers to navigate and fully grasp the connections between these approaches. This paper introduces a unifying framework inspired by mutual information, which proposes a new loss function with flexible priors. By carefully specifying these priors, we demonstrate that many existing algorithms, such as SimPO, TDPO, SparsePO, and others, can be derived from our framework. This unification offers a clearer and more structured approach, allowing researchers to understand the relationships between different DPO variants better. We aim to simplify the landscape of DPO algorithms, making it easier for the research community to gain insights and foster further advancements in LLM alignment. Ultimately, we hope our framework can be a foundation for developing more robust and interpretable alignment techniques.

We present Snapshot-QAOA, a variation of the Quantum Approximate Optimization Algorithm (QAOA) that finds approximate minimum energy eigenstates of a large set of quantum Hamiltonians (i.e. Hamiltonians with non-diagonal terms). Traditionally, QAOA targets the task of approximately solving combinatorial optimization problems; Snapshot-QAOA enables a significant expansion of the use case space for QAOA to more general quantum Hamiltonians, where the goal is to approximate the ground-state. Such ground-state finding is a common challenge in quantum chemistry and material science applications. Snapshot-QAOA retains desirable variational-algorithm qualities of QAOA, in particular small parameter count and relatively shallow circuit depth. Snapshot-QAOA is thus a better trainable alternative to the NISQ-era Variational Quantum Eigensolver (VQE) algorithm, while retaining a significant circuit-depth advantage over the QEC-era Quantum Phase Estimation (QPE) algorithm. Our fundamental approach is inspired by the idea of Trotterization of a continuous-time linear adiabatic anneal schedule, which for sufficiently large QAOA depth gives very good performance. Snapshot-QAOA restricts the QAOA evolution to not phasing out the mixing Hamiltonian completely at the end of the evolution, instead evolving only a partial typical linear QAOA schedule, thus creating a type of snapshot of the typical QAOA evolution. As a test case, we simulate Snapshot-QAOA on a particular 16 qubit J1-J2 frustrated square transverse field Ising model with periodic boundary conditions.

Revolutionary sixth-generation wireless communications technologies and applications, notably digital twin networks (DTN), connected autonomous vehicles (CAVs), space-air-ground integrated networks (SAGINs), zero-touch networks, industry 5.0, and healthcare 5.0, are driving next-generation wireless networks (NGWNs). These technologies generate massive data, requiring swift transmission and trillions of device connections, fueling the need for sophisticated next-generation multiple access (NGMA) schemes. NGMA enables massive connectivity in the 6G era, optimizing NGWN operations beyond current multiple access (MA) schemes. This survey showcases non-orthogonal multiple access (NOMA) as NGMA's frontrunner, exploring What has NOMA delivered?, What is NOMA providing?, and What lies ahead?. We present NOMA variants, fundamental operations, and applicability in multi-antenna systems, machine learning, reconfigurable intelligent surfaces (RIS), cognitive radio networks (CRN), integrated sensing and communications (ISAC), terahertz networks, and unmanned aerial vehicles (UAVs). Additionally, we explore NOMA's interplay with state-of-the-art wireless technologies, highlighting its advantages and technical challenges. Finally, we unveil NOMA research trends in the 6G era and provide design recommendations and future perspectives for NOMA as the leading NGMA solution for NGWNs.

Since the final quantum state in the Grover search algorithm is the normalized marked quantum state in the Gram-Schmidt process, Abrams and Lloyd[1] has showed that we can generate this vector by using a non-unitary gate. Following their ideas, in this paper, we present multiple explicit unitary implementations by using the square root of the non-unitary matrix and by a unitary matrix that mimics the Gram-Schmidt process. We also discuss the implementation through a linear combination of unitary matrices or similar methods and how these approximations may change the complexity. The reading of the marked element from the given circuits with high probability still requires repetitions similar to the original algorithm. However, it gives an alternative implementations which may be useful in certain platforms, Comment: The explicit circuit diagrams are given and simulated. Simulation code: https://github.com/adaskin/nonunitary-search.git

Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called deep Prototype-Based Networks (PBNs), also known as prototypical parts models. In this work, we analyze these models with respect to different properties, including interpretability. In particular, we focus on the Classification-by-Components (CBC) approach, which uses a probabilistic model to ensure interpretability and can be used as a shallow or deep architecture. We show that this model has several shortcomings, like creating contradicting explanations. Based on these findings, we propose an extension of CBC that solves these issues. Moreover, we prove that this extension has robustness guarantees and derive a loss that optimizes robustness. Additionally, our analysis shows that most (deep) PBNs are related to (deep) RBF classifiers, which implies that our robustness guarantees generalize to shallow RBF classifiers. The empirical evaluation demonstrates that our deep PBN yields state-of-the-art classification accuracy on different benchmarks while resolving the interpretability shortcomings of other approaches. Further, our shallow PBN variant outperforms other shallow PBNs while being inherently interpretable and exhibiting provable robustness guarantees., Comment: To appear at AAAI 2025. Includes the Appendix of the AAAI submission. In v2 the font size has been increased in some figures

The cost and limited capacity of fronthaul links pose significant challenges for the deployment of ultra-dense networks (UDNs), specifically for cell-free massive MIMO systems. Hence, cost-effective planning of reliable fronthaul networks is crucial for the future deployment of UDNs. We propose an optimization framework for traffic-aware hybrid fronthaul network planning, aimed at minimizing total costs through a mixed-integer linear program (MILP) that considers fiber optics and mmWave, along with optimizing key performance metrics. The results demonstrate superiority of the proposed approach, highlighting the cost-effectiveness and performance advantages when compared to different deployment schemes. Moreover, our results also reveal different trends that are critical for Service Providers (SPs) during the fronthaul planning phase of future-proof networks that can adapt to evolving traffic demands., Comment: To appear in IEEE Wireless Communications Letters

TalkWithMachines aims to enhance human-robot interaction by contributing to interpretable industrial robotic systems, especially for safety-critical applications. The presented paper investigates recent advancements in Large Language Models (LLMs) and Vision Language Models (VLMs), in combination with robotic perception and control. This integration allows robots to understand and execute commands given in natural language and to perceive their environment through visual and/or descriptive inputs. Moreover, translating the LLM's internal states and reasoning into text that humans can easily understand ensures that operators gain a clearer insight into the robot's current state and intentions, which is essential for effective and safe operation. Our paper outlines four LLM-assisted simulated robotic control workflows, which explore (i) low-level control, (ii) the generation of language-based feedback that describes the robot's internal states, (iii) the use of visual information as additional input, and (iv) the use of robot structure information for generating task plans and feedback, taking the robot's physical capabilities and limitations into account. The proposed concepts are presented in a set of experiments, along with a brief discussion. Project description, videos, and supplementary materials will be available on the project website: https://talk-machines.github.io., Comment: This paper has been accepted for publication in the proceedings of the 2024 Eighth IEEE International Conference on Robotic Computing (IRC)

The exploration of automated wrist fracture recognition has gained considerable research attention in recent years. In practical medical scenarios, physicians and surgeons may lack the specialized expertise required for accurate X-ray interpretation, highlighting the need for machine vision to enhance diagnostic accuracy. However, conventional recognition techniques face challenges in discerning subtle differences in X-rays when classifying wrist pathologies, as many of these pathologies, such as fractures, can be small and hard to distinguish. This study tackles wrist pathology recognition as a fine-grained visual recognition (FGVR) problem, utilizing a limited, custom-curated dataset that mirrors real-world medical constraints, relying solely on image-level annotations. We introduce a specialized FGVR-based ensemble approach to identify discriminative regions within X-rays. We employ an Explainable AI (XAI) technique called Grad-CAM to pinpoint these regions. Our ensemble approach outperformed many conventional SOTA and FGVR techniques, underscoring the effectiveness of our strategy in enhancing accuracy in wrist pathology recognition.

In this paper, we consider matrices given as a linear combination of permutations and analyze the impact of bit and phase flips on the perturbation of the eigenvalues. When the coefficients in the linear combination are positive, we observe that the eigenvalues of the resulting matrices are resilient to quantum bit-flip errors. In addition, we analyze the bit flips in combination with positive and negative coefficients and the phase flips. Although matrices with mixed-sign coefficients are less resilient to the bit-flip and phase-flip errors,the numerical evidence shows that the perturbation of the eigenspectrum is very small when the rate of these errors is small. We also discuss the situation when this matrix is implemented through block encoding and there is a control register. Since any square matrix can be written as a sum of permutations with some coefficients, this paper gives a framework to study matrix computations in quantum algorithms related to numerical linear algebra. In addition, it can give ideas to design more error-resilient algorithms that may involve quantum registers with different error characteristics., Comment: any comments are welcome!

Understanding the deep meanings of the Qur'an and bridging the language gap between modern standard Arabic and classical Arabic is essential to improve the question-and-answer system for the Holy Qur'an. The Qur'an QA 2023 shared task dataset had a limited number of questions with weak model retrieval. To address this challenge, this work updated the original dataset and improved the model accuracy. The original dataset, which contains 251 questions, was reviewed and expanded to 629 questions with question diversification and reformulation, leading to a comprehensive set of 1895 categorized into single-answer, multi-answer, and zero-answer types. Extensive experiments fine-tuned transformer models, including AraBERT, RoBERTa, CAMeLBERT, AraELECTRA, and BERT. The best model, AraBERT-base, achieved a MAP@10 of 0.36 and MRR of 0.59, representing improvements of 63% and 59%, respectively, compared to the baseline scores (MAP@10: 0.22, MRR: 0.37). Additionally, the dataset expansion led to improvements in handling "no answer" cases, with the proposed approach achieving a 75% success rate for such instances, compared to the baseline's 25%. These results demonstrate the effect of dataset improvement and model architecture optimization in increasing the performance of QA systems for the Holy Qur'an, with higher accuracy, recall, and precision.

Rapid advancements in Large Language models (LLMs) has significantly enhanced their reasoning capabilities. Despite improved performance on benchmarks, LLMs exhibit notable gaps in their cognitive processes. Additionally, as reflections of human-generated data, these models have the potential to inherit cognitive biases, raising concerns about their reasoning and decision making capabilities. In this paper we present a framework to interpret, understand and provide insights into a host of cognitive biases in LLMs. Conducting our research on frontier language models we're able to elucidate reasoning limitations and biases, and provide reasoning behind these biases by constructing influence graphs that identify phrases and words most responsible for biases manifested in LLMs. We further investigate biases such as round number bias and cognitive bias barrier revealed when noting framing effect in language models.

Plastic flow is conventionally treated as continuous in finite element (FE) codes, whether in isotropic, anisotropic plasticity, or crystal plasticity. This approach, derived from continuum mechanics, contradicts the intermittent nature of plasticity at the elementary scale. Understanding crystal plasticity at micro-scale opens the door to new engineering applications, such as microscale machining. In this work, a new approach is proposed to account for the intermittence of plastic deformation while remaining within the framework of continuum mechanics. We introduce a material parameter, the plastic deformation threshold, denoted as $\Delta p_{min}$, corresponding to the plastic deformation carried by the minimal plastic deformation burst within the material. The incremental model is based on the traditional predictor-corrector algorithm to calculate the elastoplastic behavior of a material subjected to any external loading. The model is presented within the framework of small deformations for von Mises plasticity. To highlight the main features of the approach, the plastic strain increment is calculated using normality rule and consistency conditions, and is accepted only if it exceeds $\Delta p_{min}$. To achieve this, a time-discontinuous generalization of the Karush-Kuhn-Tucker (KKT) conditions is proposed. The simulations show that the introduction of the plastic threshold allows for the reproduction of the spatiotemporal intermittence of plastic flow, capturing the self-organization of plastic flow in complex loading scenarios within an FE model.

Recent advances in dataset distillation have led to solutions in two main directions. The conventional batch-to-batch matching mechanism is ideal for small-scale datasets and includes bi-level optimization methods on models and syntheses, such as FRePo, RCIG, and RaT-BPTT, as well as other methods like distribution matching, gradient matching, and weight trajectory matching. Conversely, batch-to-global matching typifies decoupled methods, which are particularly advantageous for large-scale datasets. This approach has garnered substantial interest within the community, as seen in SRe$^2$L, G-VBSM, WMDD, and CDA. A primary challenge with the second approach is the lack of diversity among syntheses within each class since samples are optimized independently and the same global supervision signals are reused across different synthetic images. In this study, we propose a new Diversity-driven EarlyLate Training (DELT) scheme to enhance the diversity of images in batch-to-global matching with less computation. Our approach is conceptually simple yet effective, it partitions predefined IPC samples into smaller subtasks and employs local optimizations to distill each subset into distributions from distinct phases, reducing the uniformity induced by the unified optimization process. These distilled images from the subtasks demonstrate effective generalization when applied to the entire task. We conduct extensive experiments on CIFAR, Tiny-ImageNet, ImageNet-1K, and its sub-datasets. Our approach outperforms the previous state-of-the-art by 2$\sim$5% on average across different datasets and IPCs (images per class), increasing diversity per class by more than 5% while reducing synthesis time by up to 39.3% for enhancing the training efficiency. Code is available at: https://github.com/VILA-Lab/DELT.

Gravitational waves (GW), predicted by Einstein's General Theory of Relativity, provide a powerful probe of astrophysical phenomena and fundamental physics. In this work, we propose an unsupervised anomaly detection method using variational autoencoders (VAEs) to analyze GW time-series data. By training on noise-only data, the VAE accurately reconstructs noise inputs while failing to reconstruct anomalies, such as GW signals, which results in measurable spikes in the reconstruction error. The method was applied to data from the LIGO H1 and L1 detectors. Evaluation on testing datasets containing both noise and GW events demonstrated reliable detection, achieving an area under the ROC curve (AUC) of 0.89. This study introduces VAEs as a robust, unsupervised approach for identifying anomalies in GW data, which offers a scalable framework for detecting known and potentially new phenomena in physics., Comment: The work is still in progress

We investigate the statistical and computational limits of prompt tuning for transformer-based foundation models. Our key contributions are prompt tuning on \textit{single-head} transformers with only a \textit{single} self-attention layer: (i) is universal, and (ii) supports efficient (even almost-linear time) algorithms under the Strong Exponential Time Hypothesis (SETH). Statistically, we prove that prompt tuning on such simplest possible transformers are universal approximators for sequence-to-sequence Lipschitz functions. In addition, we provide an exponential-in-$dL$ and -in-$(1/\epsilon)$ lower bound on the required soft-prompt tokens for prompt tuning to memorize any dataset with 1-layer, 1-head transformers. Computationally, we identify a phase transition in the efficiency of prompt tuning, determined by the norm of the \textit{soft-prompt-induced} keys and queries, and provide an upper bound criterion. Beyond this criterion, no sub-quadratic (efficient) algorithm for prompt tuning exists under SETH. Within this criterion, we showcase our theory by proving the existence of almost-linear time prompt tuning inference algorithms. These fundamental limits provide important necessary conditions for designing expressive and efficient prompt tuning methods for practitioners.

Chronic kidney disease (CKD) is a significant public health challenge, often progressing to end-stage renal disease (ESRD) if not detected and managed early. Early intervention, warranted by silent disease progression, can significantly reduce associated morbidity, mortality, and financial burden. In this study, we propose a novel approach to modeling CKD progression using a combination of machine learning techniques and classical statistical models. Building on the work of Liu et al. (2023), we evaluate linear models, tree-based methods, and deep learning models to extract novel predictors for CKD progression, with feature importance assessed using Shapley values. These newly identified predictors, integrated with established clinical features from the Kidney Failure Risk Equation, are then applied within the framework of Cox proportional hazards models to predict CKD progression., Comment: Findings paper presented at Machine Learning for Health (ML4H) symposium 2024, December 15-16, 2024, Vancouver, Canada, 19 pages

Internal crack detection has been a subject of focus in structural health monitoring. By focusing on crack detection in structural datasets, it is demonstrated that deep learning (DL) methods can effectively analyze seismic wave fields interacting with micro-scale cracks, which are beyond the resolution of conventional visual inspection. This work explores a novel application of DL-based key point detection technique, where cracks are localized by predicting the coordinates of four key points that define a bounding region of the crack. The study not only opens new research directions for non-visual applications but also effectively mitigates the impact of imbalanced data which poses a challenge for previous DL models, as it can be biased toward predicting the majority class (non-crack regions). Popular DL techniques, such as the Inception blocks, are used and investigated. The model shows an overall reduction in loss when applied to micro-scale crack detection and is reflected in the lower average deviation between the location of actual and predicted cracks, with an average Intersection over Union (IoU) being 0.511 for all micro cracks (greater than 0.00 micrometers) and 0.631 for larger micro cracks (greater than 4 micrometers).

We present Y-MAP-Net, a Y-shaped neural network architecture designed for real-time multi-task learning on RGB images. Y-MAP-Net, simultaneously predicts depth, surface normals, human pose, semantic segmentation and generates multi-label captions, all from a single network evaluation. To achieve this, we adopt a multi-teacher, single-student training paradigm, where task-specific foundation models supervise the network's learning, enabling it to distill their capabilities into a lightweight architecture suitable for real-time applications. Y-MAP-Net, exhibits strong generalization, simplicity and computational efficiency, making it ideal for robotics and other practical scenarios. To support future research, we will release our code publicly., Comment: 8 page paper, 6 Figures, 3 Tables

Micro Crack detection using deep neural networks (DNNs) through an automated pipeline using wave fields interacting with the damaged areas is highly sought after. These high-dimensional spatio-temporal crack data are limited, and these datasets have large dimensions in the temporal domain. The dataset presents a substantial class imbalance, with crack pixels constituting an average of only 5% of the total pixels per sample. This extreme class imbalance poses a challenge for deep learning models with the different micro-scale cracks, as the network can be biased toward predicting the majority class, generally leading to poor detection accuracy. This study builds upon the previous benchmark SpAsE-Net, an asymmetric encoder-decoder network for micro-crack detection. The impact of various activation and loss functions were examined through feature space visualization using the manifold discovery and analysis (MDA) algorithm. The optimized architecture and training methodology achieved an accuracy of 86.85%.

We study the effect of the electron wavefunction on Kohn-Luttinger superconductivity. The role of the wavefunction is encoded in a complex form factor describing the topology and geometry of the bands. We show that the electron wavefunction significantly impacts the superconducting transition temperature and superconducting order parameter. We illustrate this using the lowest Landau level form factor and find exponential enhancement of $T_c$ for the resulting topological superconductor. We find that the ideal band geometry, which favors a fractional Chern insulator in the flat band limit, has an optimal $T_c$. Finally, we apply this understanding to a model relevant to rhombohedral graphene multilayers and unravel the importance of the band geometry for achieving robust superconductivity.

Low Earth Orbit (LEO) satellite constellations have seen significant growth and functional enhancement in recent years, which integrates various capabilities like communication, navigation, and remote sensing. However, the heterogeneity of data collected by different satellites and the problems of efficient inter-satellite collaborative computation pose significant obstacles to realizing the potential of these constellations. Existing approaches struggle with data heterogeneity, varing image resolutions, and the need for efficient on-orbit model training. To address these challenges, we propose a novel decentralized PFL framework, namely, A Novel Decentra L ized Person A lized Federated Learning for Heteroge N eous LEO Satell I te Co N st E llation (ALANINE). ALANINE incorporates decentralized FL (DFL) for satellite image Super Resolution (SR), which enhances input data quality. Then it utilizes PFL to implement a personalized approach that accounts for unique characteristics of satellite data. In addition, the framework employs advanced model pruning to optimize model complexity and transmission efficiency. The framework enables efficient data acquisition and processing while improving the accuracy of PFL image processing models. Simulation results demonstrate that ALANINE exhibits superior performance in on-orbit training of SR and PFL image processing models compared to traditional centralized approaches. This novel method shows significant improvements in data acquisition efficiency, process accuracy, and model adaptability to local satellite conditions., Comment: 14 pages, 8 figures

Consider $E$ a vector bundle over a smooth curve $C$. We compute the $\delta$-invariant of all ample ($\mathbb{Q}$-) line bundles on $\mathbb{P}(E)$ when $E$ is strictly Mumford semistable. We also investigate the case when one assumes that the Harder-Narasimhan filtration of $E$ has only one step.

Machine learning methods have a groundbreaking impact in many application domains, but their application on real robotic platforms is still limited. Despite the many challenges associated with combining machine learning technology with robotics, robot learning remains one of the most promising directions for enhancing the capabilities of robots. When deploying learning-based approaches on real robots, extra effort is required to address the challenges posed by various real-world factors. To investigate the key factors influencing real-world deployment and to encourage original solutions from different researchers, we organized the Robot Air Hockey Challenge at the NeurIPS 2023 conference. We selected the air hockey task as a benchmark, encompassing low-level robotics problems and high-level tactics. Different from other machine learning-centric benchmarks, participants need to tackle practical challenges in robotics, such as the sim-to-real gap, low-level control issues, safety problems, real-time requirements, and the limited availability of real-world data. Furthermore, we focus on a dynamic environment, removing the typical assumption of quasi-static motions of other real-world benchmarks. The competition's results show that solutions combining learning-based approaches with prior knowledge outperform those relying solely on data when real-world deployment is challenging. Our ablation study reveals which real-world factors may be overlooked when building a learning-based solution. The successful real-world air hockey deployment of best-performing agents sets the foundation for future competitions and follow-up research directions., Comment: Accept at NeurIPS 2024 Dataset and Benchmark Track

In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object detection approaches, we have observed widespread inconsistencies among them regarding the datasets, metrics, and scenarios used, alongside a notable absence of a clear definition for unknown objects, which hampers meaningful evaluation. To counter these issues, we introduce two benchmarks: a unified VOC-COCO evaluation, and the new OpenImagesRoad benchmark which provides clear hierarchical object definition besides new evaluation metrics. Complementing the benchmark, we exploit recent self-supervised Vision Transformers performance, to improve pseudo-labeling-based OpenSet Object Detection (OSOD), through OW-DETR++. State-of-the-art methods are extensively evaluated on the proposed benchmarks. This study provides a clear problem definition, ensures consistent evaluations, and draws new conclusions about effectiveness of OSOD strategies., Comment: Accepted at ECCV 2024 Workshop: "The 3rd Workshop for Out-of-Distribution Generalization in Computer Vision Foundation Models"

We consider a strategic decision-making problem where a logistics provider (LP) seeks to locate collection and delivery points (CDPs) with the objective to reduce total logistics costs. The customers maximize utility that depends on their perception of home delivery service as well as the characteristics of the CDPs, including their location. At the strategic planning level, the LP does not have complete information about customers' preferences and their exact location. We introduce a mixed integer non-linear formulation of the problem and propose two linear reformulations. The latter involve sample average approximations and closest assignment constraints, and in one of the formulations we use scenario aggregation to reduce its size. We solve the formulations with a general-purpose solver using a standard Benders decomposition method. Based on extensive computational results and a realistic case study, we find that the problem can be solved efficiently. However, the level of uncertainty in the instances determines which approach is the most efficient. We use an entropy measure to capture the level of uncertainty that can be computed prior to solving. Furthermore, the results highlight the value of accurate demand modeling, as customer preferences have an important impact on the solutions and associated costs.

We introduce Agent K v1.0, an end-to-end autonomous data science agent designed to automate, optimise, and generalise across diverse data science tasks. Fully automated, Agent K v1.0 manages the entire data science life cycle by learning from experience. It leverages a highly flexible structured reasoning framework to enable it to dynamically process memory in a nested structure, effectively learning from accumulated experience stored to handle complex reasoning tasks. It optimises long- and short-term memory by selectively storing and retrieving key information, guiding future decisions based on environmental rewards. This iterative approach allows it to refine decisions without fine-tuning or backpropagation, achieving continuous improvement through experiential learning. We evaluate our agent's apabilities using Kaggle competitions as a case study. Following a fully automated protocol, Agent K v1.0 systematically addresses complex and multimodal data science tasks, employing Bayesian optimisation for hyperparameter tuning and feature engineering. Our new evaluation framework rigorously assesses Agent K v1.0's end-to-end capabilities to generate and send submissions starting from a Kaggle competition URL. Results demonstrate that Agent K v1.0 achieves a 92.5\% success rate across tasks, spanning tabular, computer vision, NLP, and multimodal domains. When benchmarking against 5,856 human Kaggle competitors by calculating Elo-MMR scores for each, Agent K v1.0 ranks in the top 38\%, demonstrating an overall skill level comparable to Expert-level users. Notably, its Elo-MMR score falls between the first and third quartiles of scores achieved by human Grandmasters. Furthermore, our results indicate that Agent K v1.0 has reached a performance level equivalent to Kaggle Grandmaster, with a record of 6 gold, 3 silver, and 7 bronze medals, as defined by Kaggle's progression system.

While overparameterization is known to benefit generalization, its impact on Out-Of-Distribution (OOD) detection is less understood. This paper investigates the influence of model complexity in OOD detection. We propose an expected OOD risk metric to evaluate classifiers confidence on both training and OOD samples. Leveraging Random Matrix Theory, we derive bounds for the expected OOD risk of binary least-squares classifiers applied to Gaussian data. We show that the OOD risk depicts an infinite peak, when the number of parameters is equal to the number of samples, which we associate with the double descent phenomenon. Our experimental study on different OOD detection methods across multiple neural architectures extends our theoretical insights and highlights a double descent curve. Our observations suggest that overparameterization does not necessarily lead to better OOD detection. Using the Neural Collapse framework, we provide insights to better understand this behavior. To facilitate reproducibility, our code will be made publicly available upon publication.

Advancements in AI heavily rely on large-scale datasets meticulously curated and annotated for training. However, concerns persist regarding the transparency and context of data collection methodologies, especially when sourced through crowdsourcing platforms. Crowdsourcing often employs low-wage workers with poor working conditions and lacks consideration for the representativeness of annotators, leading to algorithms that fail to represent diverse views and perpetuate biases against certain groups. To address these limitations, we propose a methodology involving a co-design model that actively engages stakeholders at key stages, integrating principles of Equity, Diversity, and Inclusion (EDI) to ensure diverse viewpoints. We apply this methodology to develop a dataset and AI model for evaluating public space quality using street view images, demonstrating its effectiveness in capturing diverse perspectives and fostering higher-quality data., Comment: Presented at CVPR 2024 Workshop on Responsible Data

Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since human values can be personalized and dynamically change over time, the desirable levels of value alignment vary across different ethnic groups, industry sectors, and user cohorts. Within existing frameworks, it is hard to define human values and align AI systems accordingly across different directions simultaneously, such as harmlessness, helpfulness, and positiveness. To address this, we develop a novel, first-principle approach called Multi-Human-Value Alignment Palette (MAP), which navigates the alignment across multiple human values in a structured and reliable way. MAP formulates the alignment problem as an optimization task with user-defined constraints, which define human value targets. It can be efficiently solved via a primal-dual approach, which determines whether a user-defined alignment target is achievable and how to achieve it. We conduct a detailed theoretical analysis of MAP by quantifying the trade-offs between values, the sensitivity to constraints, the fundamental connection between multi-value alignment and sequential alignment, and proving that linear weighted rewards are sufficient for multi-value alignment. Extensive experiments demonstrate MAP's ability to align multiple values in a principled manner while delivering strong empirical performance across various tasks.

With the rapid advancement of autonomous driving technology, efficient and accurate object detection capabilities have become crucial factors in ensuring the safety and reliability of autonomous driving systems. However, in low-visibility environments such as hazy conditions, the performance of traditional object detection algorithms often degrades significantly, failing to meet the demands of autonomous driving. To address this challenge, this paper proposes two innovative deep learning models: YOLO-Vehicle and YOLO-Vehicle-Pro. YOLO-Vehicle is an object detection model tailored specifically for autonomous driving scenarios, employing multimodal fusion techniques to combine image and textual information for object detection. YOLO-Vehicle-Pro builds upon this foundation by introducing an improved image dehazing algorithm, enhancing detection performance in low-visibility environments. In addition to model innovation, this paper also designs and implements a cloud-edge collaborative object detection system, deploying models on edge devices and offloading partial computational tasks to the cloud in complex situations. Experimental results demonstrate that on the KITTI dataset, the YOLO-Vehicle-v1s model achieved 92.1% accuracy while maintaining a detection speed of 226 FPS and an inference time of 12ms, meeting the real-time requirements of autonomous driving. When processing hazy images, the YOLO-Vehicle-Pro model achieved a high accuracy of 82.3% mAP@50 on the Foggy Cityscapes dataset while maintaining a detection speed of 43 FPS.

The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to advances in next generation computing hardware. AI has the potential to accelerate materials discovery and design by more effectively exploring the chemical space compared to other computational methods or by trial-and-error. While substantial progress has been made on AI for materials data, benchmarks, and models, a barrier that has emerged is the lack of publicly available training data and open pre-trained models. To address this, we present a Meta FAIR release of the Open Materials 2024 (OMat24) large-scale open dataset and an accompanying set of pre-trained models. OMat24 contains over 110 million density functional theory (DFT) calculations focused on structural and compositional diversity. Our EquiformerV2 models achieve state-of-the-art performance on the Matbench Discovery leaderboard and are capable of predicting ground-state stability and formation energies to an F1 score above 0.9 and an accuracy of 20 meV/atom, respectively. We explore the impact of model size, auxiliary denoising objectives, and fine-tuning on performance across a range of datasets including OMat24, MPtraj, and Alexandria. The open release of the OMat24 dataset and models enables the research community to build upon our efforts and drive further advancements in AI-assisted materials science., Comment: 19 pages

In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing across diverse environments due to their limited grasp of the underlying decision dynamics. In contrast, large language models (LLMs) have recently emerged as powerful general-purpose tools, due to their capacity to maintain vast amounts of domain-specific knowledge. To harness this rich prior knowledge for efficiently solving complex SDM tasks, we propose treating LLMs as prior action distributions and integrating them into RL frameworks through Bayesian inference methods, making use of variational inference and direct posterior sampling. The proposed approaches facilitate the seamless incorporation of fixed LLM priors into both policy-based and value-based RL frameworks. Our experiments show that incorporating LLM-based action priors significantly reduces exploration and optimization complexity, substantially improving sample efficiency compared to traditional RL techniques, e.g., using LLM priors decreases the number of required samples by over 90% in offline learning scenarios.