Search

This study explores a green pathway for urea synthesis using plasma-ice interaction with gas mixtures of N2 + CO2 and NH3 + CO2. Electrical and optical emission spectroscopy were employed to characterize the plasmas, revealing that urea formation involves complex reactions driven by high-energy species, producing reactive nitrogen and carbon intermediates that further react to form urea. Physicochemical analyses of plasma-treated ice showed increased pH, electrical conductivity (EC), and reduced oxidation-reduction potential (ORP). Optimization of plasma process parameters (gas pressure, applied voltage, and treatment time) was performed to enhance urea formation. Among these parameters, plasma treatment time had the most substantial influence. Increasing treatment time from 20 to 60 minutes significantly impacted physicochemical properties: for N2 + CO2 plasma, pH increased by 21.05%, EC by 184.7%, and ORP decreased by 27.48%; for NH3 + CO2 plasma, pH increased by 27.37%, EC by 239.05%, and ORP decreased by 72.67%, respectively. The study shows that NH3 + CO2 plasma produces a significantly higher concentration of urea (7.7 mg L-1) compared to N2 + CO2 plasma (0.55 mg L-1). This is attributed to the direct availability and reactivity of ammonia, which simplifies reaction pathways and enhances intermediate formation. These findings highlight the potential of plasma-ice interaction as an energy-efficient and environmentally friendly method for urea synthesis, offering a sustainable alternative to conventional processes.

Landmark judgments are of prime importance in the Common Law System because of their exceptional jurisprudence and frequent references in other judgments. In this work, we leverage contextual references available in citing judgments to create an extractive summary of the target judgment. We evaluate the proposed algorithm on two datasets curated from the judgments of Indian Courts and find the results promising., Comment: Accepted for publication at ICON 2023

Cross-view geo-localization has garnered notable attention in the realm of computer vision, spurred by the widespread availability of copious geotagged datasets and the advancements in machine learning techniques. This paper provides a thorough survey of cutting-edge methodologies, techniques, and associated challenges that are integral to this domain, with a focus on feature-based and deep learning strategies. Feature-based methods capitalize on unique features to establish correspondences across disparate viewpoints, whereas deep learning-based methodologies deploy convolutional neural networks to embed view-invariant attributes. This work also delineates the multifaceted challenges encountered in cross-view geo-localization, such as variations in viewpoints and illumination, the occurrence of occlusions, and it elucidates innovative solutions that have been formulated to tackle these issues. Furthermore, we delineate benchmark datasets and relevant evaluation metrics, and also perform a comparative analysis of state-of-the-art techniques. Finally, we conclude the paper with a discussion on prospective avenues for future research and the burgeoning applications of cross-view geo-localization in an intricately interconnected global landscape.

The excitation scheme is essential for single-photon sources as it prepares the exciton state, defines the decay dynamics, and influences the spectral diffusion of the emitted single photons. Here, we investigate the impact of different optical excitation strategies on the single-photon emission characteristics of bilayer WSe$_2$ quantum emitters. Under phonon-assisted excitation, we achieve narrow and stable single-photon emission with an excellent purity reaching $ 0.94\pm 0.02\,$. Furthermore, the decay time is reduced by more than an order of magnitude from $(16.65 \pm 2.39)\,$ns for above-band excitation to $(1.33 \pm 0.04)\,$ns for phonon-assisted excitation. Finally, we observe a suppressed spectral wandering along with a two-fold reduction of the spectral linewidth. Our comprehensive investigation highlights the critical role of the excitation method in optimizing the performance of WSe$_2$-based quantum emitters.

Topological Neural Networks (TNNs) incorporate higher-order relational information beyond pairwise interactions, enabling richer representations than Graph Neural Networks (GNNs). Concurrently, topological descriptors based on persistent homology (PH) are being increasingly employed to augment the GNNs. We investigate the benefits of integrating these two paradigms. Specifically, we introduce TopNets as a broad framework that subsumes and unifies various methods in the intersection of GNNs/TNNs and PH such as (generalizations of) RePHINE and TOGL. TopNets can also be readily adapted to handle (symmetries in) geometric complexes, extending the scope of TNNs and PH to spatial settings. Theoretically, we show that PH descriptors can provably enhance the expressivity of simplicial message-passing networks. Empirically, (continuous and E(n)-equivariant extensions of) TopNets achieve strong performance across diverse tasks, including antibody design, molecular dynamics simulation, and drug property prediction., Comment: Accepted to ICML 2024

The widespread use of industrial refrigeration systems across various sectors contribute significantly to global energy consumption, highlighting substantial opportunities for energy conservation through intelligent control design. As such, this work focuses on control algorithm design in industrial refrigeration that minimize operational costs and provide efficient heat extraction. By adopting tools from inventory control, we characterize the structure of these optimal control policies, exploring the impact of different energy cost-rate structures such as time-of-use (TOU) pricing and peak pricing. While classical threshold policies are optimal under TOU costs, introducing peak pricing challenges their optimality, emphasizing the need for carefully designed control strategies in the presence of significant peak costs. We provide theoretical findings and simulation studies on this phenomenon, offering insights for more efficient industrial refrigeration management.

Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models that produce images using only a high-level text description, the vision-language model (VLM) applications will significantly impact our relationship with technology. However, there are many challenges that need to be addressed to improve the reliability of those models. While language is discrete, vision evolves in a much higher dimensional space in which concepts cannot always be easily discretized. To better understand the mechanics behind mapping vision to language, we present this introduction to VLMs which we hope will help anyone who would like to enter the field. First, we introduce what VLMs are, how they work, and how to train them. Then, we present and discuss approaches to evaluate VLMs. Although this work primarily focuses on mapping images to language, we also discuss extending VLMs to videos.

Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task. Diffusion models are a particularly promising modelling approach, enabling post-hoc conditioning and trading off quality for speed during generation. We show mathematically that permutation equivariant denoisers severely limit the expressiveness of graph diffusion models and thus their adaptation to retrosynthesis. To address this limitation, we relax the equivariance requirement such that it only applies to aligned permutations of the conditioning and the generated graphs obtained through atom mapping. Our new denoiser achieves the highest top-$1$ accuracy ($54.7$\%) across template-free and template-based methods on USPTO-50k. We also demonstrate the ability for flexible post-training conditioning and good sample quality with small diffusion step counts, highlighting the potential for interactive applications and additional controls for multi-step planning., Comment: 28 pages, 9 figures

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when outliers are present. Rotating activation or weight matrices helps remove outliers and benefits quantization. In this work, we identify a collection of applicable rotation parameterizations that lead to identical outputs in full-precision Transformer architectures while enhancing quantization accuracy. In addition, we find that some random rotations lead to much better quantization than others, with an up to 13 points difference in downstream zero-shot reasoning performance. As a result, we propose SpinQuant, a novel approach that incorporates learned rotation matrices for optimal quantized network accuracy. With 4-bit quantization of weight, activation, and KV-cache, SpinQuant narrows the accuracy gap on zero-shot reasoning tasks with full precision to merely 2.9 points on the LLaMA-2 7B model, surpassing LLM-QAT by 19.1 points and SmoothQuant by 25.0 points. Furthermore, SpinQuant also outperforms concurrent work QuaRot, which applies random rotations to remove outliers. In particular, for LLaMA-3 8B models that are hard to quantize, SpinQuant reduces the gap to full precision by up to 45.1% relative to QuaRot.

Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as personal computers and mobile/wearable devices, and results in substantial inference costs in resource-rich environments like cloud servers. To extend the use of LLMs, we introduce a low-rank decomposition approach to effectively compress these models, tailored to the requirements of specific applications. We observe that LLMs pretrained on general datasets contain many redundant components not needed for particular applications. Our method focuses on identifying and removing these redundant parts, retaining only the necessary elements for the target applications. Specifically, we represent the weight matrices of LLMs as a linear combination of base components. We then prune the irrelevant bases and enhance the model with new bases beneficial for specific applications. Deep compression results on the Llama 2-7b and -13B models, conducted on target applications including mathematical reasoning and code generation, show that our method significantly reduces model size while maintaining comparable accuracy to state-of-the-art low-rank compression techniques.

The success of denoising diffusion models in representing rich data distributions over 2D raster images has prompted research on extending them to other data representations, such as vector graphics. Unfortunately due to their variable structure and scarcity of vector training data, directly applying diffusion models on this domain remains a challenging problem. Using workarounds like optimization via Score Distillation Sampling (SDS) is also fraught with difficulty, as vector representations are non trivial to directly optimize and tend to result in implausible geometries such as redundant or self-intersecting shapes. NIVeL addresses these challenges by reinterpreting the problem on an alternative, intermediate domain which preserves the desirable properties of vector graphics -- mainly sparsity of representation and resolution-independence. This alternative domain is based on neural implicit fields expressed in a set of decomposable, editable layers. Based on our experiments, NIVeL produces text-to-vector graphics results of significantly better quality than the state-of-the-art.

Preferential Bayesian optimization (PBO) is a sample-efficient framework for learning human preferences between candidate designs. PBO classically relies on homoscedastic noise models to represent human aleatoric uncertainty. Yet, such noise fails to accurately capture the varying levels of human aleatoric uncertainty, particularly when the user possesses partial knowledge among different pairs of candidates. For instance, a chemist with solid expertise in glucose-related molecules may easily compare two compounds from that family while struggling to compare alcohol-related molecules. Currently, PBO overlooks this uncertainty during the search for a new candidate through the maximization of the acquisition function, consequently underestimating the risk associated with human uncertainty. To address this issue, we propose a heteroscedastic noise model to capture human aleatoric uncertainty. This model adaptively assigns noise levels based on the distance of a specific input to a predefined set of reliable inputs known as anchors provided by the human. Anchors encapsulate partial knowledge and offer insight into the comparative difficulty of evaluating different candidate pairs. Such a model can be seamlessly integrated into the acquisition function, thus leading to candidate design pairs that elegantly trade informativeness and ease of comparison for the human expert. We perform an extensive empirical evaluation of the proposed approach, demonstrating a consistent improvement over homoscedastic PBO.

This study presents a novel and ecofriendly method for synthesizing ammonium nitrate using activated prepared through air and ammonia plasma treatments. Initially, PAW containing nitrate ions is produced by treating water with air plasma. This PAW air is then frozen and exposed to low pressure NH$_3$ plasma, introducing ammonium ions to from NH$_4$NO$_3$. We systematically investigate the voltage current characteristics of the air and NH$_3$ plasma, analyze the generated species and radicals to understand the mechanism of NH$_4$NO$_3$ formation, and evaluate the effects of process parameters such as NH$_3$ gas pressure, applied voltage, and treatment time on the properties of PAW. Our results indicate that all examined process parameters positively influence the properties of PAW. Among these parameters, the duration of NH$_3$ plasma treatment of PAW ice exerts the most significant effect. Specifically, the concentration of NH4 ions increased by 134.2 percent when the NH$_3$ treatment time was extended from 0.5 h to 1 h, compared to 12.7 and 33.3 percent increases for NH$_3$ pressure, ranging from 0.25 to 0.55 mbar, and applied voltage, ranging from 500 to 700 V, respectively. Similarly, variations in pH, oxidation reduction potential, and electrical conductivity were substantially higher with increased treatment time than with changes in gas pressure and applied voltage. The PAW exhibited a neutral to slightly basic pH, making it ideal for soil applications, thereby addressing the existing issue of the high acidity of PAW and its use in agriculture.

Leakage out of the computational subspace is a major limitation of current state-of-the-art neutral-atom quantum computers and a significant challenge for scalable systems. In a quantum processor with cesium atoms, we demonstrate proof-of-principle circuit-based conversion of leakage errors to erasure errors via Leakage Detection Units (LDUs), which non-destructively map information about the presence or absence of the qubit onto the state of an ancilla. With a standard LDU circuit, we successfully convert leakage errors to erasure errors for all major leakage pathways while preserving the quantum information in the case that no leakage occurred. We benchmark the performance of the LDU using a three-outcome low-loss state detection method and also explore the advantages of three-outcome measurements for LDUs. We find that the LDU detects atom-loss errors with ~93.4% accuracy, limited by technical imperfections of our apparatus. We further compile and execute a SWAP LDU, wherein the roles of the original data atom and ancilla atom are exchanged under the action of the LDU, providing 'free refilling' of atoms in the case of leakage errors. This circuit-based leakage-to-erasure error conversion is a critical component of a neutral-atom quantum processor where the quantum information may significantly outlive the lifetime of any individual atom in the quantum register.

We present a coupled mechanistic approach that elucidates the intricate interplay between stress and electrochemistry, enabling the prediction of the onset of instabilities in Li-metal anodes and the solid electrolyte interphase (SEI) in liquid-electrolyte Li-metal batteries. Our continuum theory considers a two-way coupling between stress and electrochemistry, includes Li and electron transport through SEI, incorporates effects of Li viscoplasticity, includes SEI and electrolyte interface surface energy and evaluates crucial roles of these mechanistic effects on the continuously evolving anode surface due to the viscoplastic deformation of lithium. In the model, spatial current density evolves with the stress-induced potential across the deformed anode/SEI interface. We assume SEI as a homogeneous, artificial layer on the Li-anode, which allows the investigation of the mechanical and electrochemical properties of the SEI systematically. Subsequently, we solve a set of coupled electrochemistry and displacement equations within the SEI and anode domains. The model is implemented numerically by writing a user element subroutine in Abaqus/Standard. We conduct numerical simulations under various galvanostatic conditions and SEI properties and predict conditions for anode instability. We find that Li viscoplasticity is one of the key attributes that drives instability in the Li-anode and show that applying a soft artificial SEI layer on the Li-anode to minimize viscoplastic deformation can be an effective method. We also report the role of artificial SEI elasticity and thickness on anode stability. Selected stability maps are provided as a design aid for artificial SEI.

The energy market, and specifically the renewable sector carries volatility and risks, similar to the financial market. Here, we leverage on a well-established, return-risk approach, commonly used by equity portfolio-managers and apply it to energy resources. We visualize the relationship between the resources' costs and their risks in terms of efficient frontiers. We apply this analysis to publically available data for various US regions: Central, Eastern and Western coasts. Since risk management is contingent on costs, this approach sheds useful light in assessing dynamic pricing in modern electrical grids. By integrating geographical and temporal dimensions into our research, we aim at providing more nuanced and context-specific recommendations for energy resource allocation. This approach may help decision-makers in the renewable energy sector to make informed choices that account for regional variations, climatic conditions, and long-term performance trends., Comment: 9 pages, 3 figures, 10 ref

Buildings account for 40 % of global energy consumption. A considerable portion of building energy consumption stems from heating, ventilation, and air conditioning (HVAC), and thus implementing smart, energy-efficient HVAC systems has the potential to significantly impact the course of climate change. In recent years, model-free reinforcement learning algorithms have been increasingly assessed for this purpose due to their ability to learn and adapt purely from experience. They have been shown to outperform classical controllers in terms of energy cost and consumption, as well as thermal comfort. However, their weakness lies in their relatively poor data efficiency, requiring long periods of training to reach acceptable policies, making them inapplicable to real-world controllers directly. Hence, common research goals are to improve the learning speed, as well as to improve their ability to generalize, in order to facilitate transfer learning to unseen building environments. In this paper, we take a federated learning approach to training the reinforcement learning controller of an HVAC system. A global control policy is learned by aggregating local policies trained on multiple data centers located in different climate zones. The goal of the policy is to simultaneously minimize energy consumption and maximize thermal comfort. The federated optimization strategy indirectly increases both the rate at which experience data is collected and the variation in the data. We demonstrate through experimental evaluation that these effects lead to a faster learning speed, as well as greater generalization capabilities in the federated policy compared to any individually trained policy.

The study investigates the potential of Plasma-Activated Water (PAW) as a nitrogen supplement in hydroponic cultivation (HS-N+PAW), specifically focusing on radish seed germination and plant growth. PAW, produced using a dielectric barrier discharge pencil plasma jet using air as plasma forming gas, is compared against conventional hydroponic solution (HS) and hydroponic solution without nitrogen (HS-N). PAW treatment completely eliminates microbial growth in seeds. Radish plants cultivated with HS-N+PAW display approximately 30% and 3% longer roots compared to those grown with HS-N and HS, respectively, with shoot length increasing by ~16.5% (HS-N) and <1% (HS). Root weight sees a substantial increase of ~51% with HS-N+PAW compared to HS-N, while the increase with HS is not significant. Similarly, shoot fresh weight sees a notable increase of 50% (HS-N) and 10% (HS). In terms of biochemical composition, radish roots show a significant increase of approximately 15.3% in soluble sugar concentration with HS-N+PAW compared to HS-N. Protein concentration in radish leaves increases by ~5.1% and ~19.0% with HS-N+PAW compared to HS-N and HS, respectively. Heightened soluble sugar and protein concentrations in HS-N+PAW-grown plants, indicating enhanced metabolic activity and nutrient uptake. However, variations in chlorophyll and carotenoid concentrations in leaves among different growth media are statistically insignificant. H2O2 concentration root and shoot remains consistent across growth media, electrolytic and phenolic leakage, along with antioxidant enzyme activities, exhibit differential responses, underscoring the impact of growth conditions on plant stress responses.

Present-day graphical user interfaces (GUIs) exhibit diverse arrangements of text, graphics, and interactive elements such as buttons and menus, but representations of GUIs have not kept up. They do not encapsulate both semantic and visuo-spatial relationships among elements. To seize machine learning's potential for GUIs more efficiently, Graph4GUI exploits graph neural networks to capture individual elements' properties and their semantic-visuo-spatial constraints in a layout. The learned representation demonstrated its effectiveness in multiple tasks, especially generating designs in a challenging GUI autocompletion task, which involved predicting the positions of remaining unplaced elements in a partially completed GUI. The new model's suggestions showed alignment and visual appeal superior to the baseline method and received higher subjective ratings for preference. Furthermore, we demonstrate the practical benefits and efficiency advantages designers perceive when utilizing our model as an autocompletion plug-in., Comment: 18 pages

Thin film detectors which incorporate semiconductor materials other than silicon have the potential to build upon their unique material properties and offer advantages such as faster response times, operation at room temperature, and radiation hardness. To explore the possibility, promising candidate materials were selected, and particle tracking detectors were fabricated. An indium phosphide detector with a metal-insulator-metal (MIM) structure has been fabricated for particle tracking. The detector was tested using radioactive sources and a high energy proton beam at Fermi National Accelerator Laboratory. In addition to its simplistic design and fabrication process, the indium phosphide particle detector showed a very fast response time of hundreds of picoseconds for the 120 GeV protons, which are comparable to the ultra-fast silicon detectors. This fast-timing response is attributed to the high electron mobility of indium phosphide. Such material properties can be leveraged to build novel detectors with superlative performance., Comment: 10 pages, 7 figures

Because dark excitons in quantum dots are not directly optically accessible, so far they have not played a significant role in using quantum dots for photon generation. They possess significantly longer lifetimes than their brighter counterparts and hence offer enormous potential for photon storage or manipulation. In this work, we demonstrate an all-optical storage and retrieval of the spin-forbidden dark exciton in a quantum dot from the ground state employing chirped pulses and an in-plane magnetic field. Our experimental findings are in excellent agreement with theoretical predictions of the dynamics calculated using state-of-the-art product tensor methods. Our scheme enables an all-optical control of dark states without relying on any preceding decays. This opens up a new dimension for optimal quantum control and time-bin entangled photon pair generation from quantum dots.

The emergence of quantum computing presents a double-edged sword for cybersecurity. While its immense power holds promise for advancements in various fields, it also threatens to crack the foundation of current encryption methods. This analysis explores the impact of quantum computing on critical infrastructure and cloud services, meticulously evaluating potential vulnerabilities across various layers, including applications, data, runtime, middleware, operating systems, virtualization, hardware, storage, and networks. We advocate for proactive security strategies and collaboration between sectors to develop and implement quantum-resistant cryptography. This crucial shift necessitates a comprehensive approach, and the paper introduces a tailored security blueprint encompassing nine critical infrastructure components. This blueprint strengthens each area's defenses against potential quantum-induced cyber threats. Our strategic vulnerability and risk assessment equips stakeholders with the knowledge to navigate the complex quantum threat landscape. This empowers them to make informed decisions about design, implementation, and policy formulation, ultimately bolstering the resilience of critical infrastructure. In essence, this analysis not only forecasts quantum threats but also offers a sophisticated, actionable framework for fortifying infrastructure and cloud environments against the multifaceted challenges of the quantum era. This proactive approach will ensure continued data security and a thriving digital landscape in the years to come

In-Memory Computing (IMC) introduces a new paradigm of computation that offers high efficiency in terms of latency and power consumption for AI accelerators. However, the non-idealities and defects of emerging technologies used in advanced IMC can severely degrade the accuracy of inferred Neural Networks (NN) and lead to malfunctions in safety-critical applications. In this paper, we investigate an architectural-level mitigation technique based on the coordinated action of multiple checksum codes, to detect and correct errors at run-time. This implementation demonstrates higher efficiency in recovering accuracy across different AI algorithms and technologies compared to more traditional methods such as Triple Modular Redundancy (TMR). The results show that several configurations of our implementation recover more than 91% of the original accuracy with less than half of the area required by TMR and less than 40% of latency overhead., Comment: This paper will be presented at 29th IEEE European Test Symposium 2024 (ETS) 2024

Climate and weather prediction traditionally relies on complex numerical simulations of atmospheric physics. Deep learning approaches, such as transformers, have recently challenged the simulation paradigm with complex network forecasts. However, they often act as data-driven black-box models that neglect the underlying physics and lack uncertainty quantification. We address these limitations with ClimODE, a spatiotemporal continuous-time process that implements a key principle of advection from statistical mechanics, namely, weather changes due to a spatial movement of quantities over time. ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow, which also enables estimating the uncertainty in predictions. Our approach outperforms existing data-driven methods in global and regional forecasting with an order of magnitude smaller parameterization, establishing a new state of the art., Comment: Accepted as ICLR 2024 Oral. Project website: https://yogeshverma1998.github.io/ClimODE/

Entangled photon pairs form the foundation for many applications in the realm of quantum communication. For fiber-optic transfer of entangled photon pairs, time-bin encoding can potentially offer an improved stability compared to polarization encoded qubits. Here, we lay the theoretical foundations to describe the measurement of time-bin entangled photons. We derive multi-time correlation functions of the time-bin encoded photon pairs, corresponding to quantum state tomographic measurements. Our theory can be the starting point to extend the simulations to include all kinds of loss or decoherence effects that apply in a specific quantum system for realistic simulation for time-bin entanglement from quantum emitters., Comment: 8 pages, 3 figures

The emergence of quantum computing poses a formidable security challenge to network protocols traditionally safeguarded by classical cryptographic algorithms. This paper provides an exhaustive analysis of vulnerabilities introduced by quantum computing in a diverse array of widely utilized security protocols across the layers of the TCP/IP model, including TLS, IPsec, SSH, PGP, and more. Our investigation focuses on precisely identifying vulnerabilities susceptible to exploitation by quantum adversaries at various migration stages for each protocol while also assessing the associated risks and consequences for secure communication. We delve deep into the impact of quantum computing on each protocol, emphasizing potential threats posed by quantum attacks and scrutinizing the effectiveness of post-quantum cryptographic solutions. Through carefully evaluating vulnerabilities and risks that network protocols face in the post-quantum era, this study provides invaluable insights to guide the development of appropriate countermeasures. Our findings contribute to a broader comprehension of quantum computing's influence on network security and offer practical guidance for protocol designers, implementers, and policymakers in addressing the challenges stemming from the advancement of quantum computing. This comprehensive study is a crucial step toward fortifying the security of networked environments in the quantum age.

The rise of large-scale quantum computing poses a significant threat to traditional cryptographic security measures. Quantum attacks undermine current asymmetric cryptographic algorithms, rendering them ineffective. Even symmetric key cryptography is vulnerable, albeit to a lesser extent, suggesting longer keys or extended hash functions for security. Thus, current cryptographic solutions are inadequate against emerging quantum threats. Organizations must transition to quantum-safe environments with robust continuity plans and meticulous risk management. This study explores the challenges of migrating to quantum-safe cryptographic states, introducing a comprehensive security risk assessment framework. We propose a security risk assessment framework that examines vulnerabilities across algorithms, certificates, and protocols throughout the migration process (pre-migration, during migration, post-migration). We link these vulnerabilities to the STRIDE threat model to assess their impact and likelihood. Then, we discuss practical mitigation strategies for critical components like algorithms, public key infrastructures, and protocols. Our study not only identifies potential attacks and vulnerabilities at each layer and migration stage but also suggests possible countermeasures and alternatives to enhance system resilience, empowering organizations to construct a secure infrastructure for the quantum era. Through these efforts, we establish the foundation for enduring security in networked systems amid the challenges of the quantum era.

Understanding how individuals focus and perform visual searches during collaborative tasks can help improve user engagement. Eye tracking measures provide informative cues for such understanding. This article presents A-DisETrac, an advanced analytic dashboard for distributed eye tracking. It uses off-the-shelf eye trackers to monitor multiple users in parallel, compute both traditional and advanced gaze measures in real-time, and display them on an interactive dashboard. Using two pilot studies, the system was evaluated in terms of user experience and utility, and compared with existing work. Moreover, the system was used to study how advanced gaze measures such as ambient-focal coefficient K and real-time index of pupillary activity relate to collaborative behavior. It was observed that the time a group takes to complete a puzzle is related to the ambient visual scanning behavior quantified and groups that spent more time had more scanning behavior. User experience questionnaire results suggest that their dashboard provides a comparatively good user experience.

Given the destructive impacts of tropical cyclones, it is critical to have a reliable system for cyclone intensity detection. Various techniques are available for this purpose, each with differing levels of accuracy. In this paper, we introduce two ensemble-based models based on AlexNet architecture to estimate tropical cyclone intensity using visible satellite images. The first model, trained on the entire dataset, is called the global AlexNet model. The second model is a distributed version of AlexNet in which multiple AlexNets are trained separately on subsets of the training data categorized according to the Saffir-Simpson wind speed scale prescribed by the meterologists. We evaluated the performance of both models against a deep learning benchmark model called \textit{Deepti} using a publicly available cyclone image dataset. Results indicate that both the global model (with a root mean square error (RMSE) of 9.03 knots) and the distributed model (with a RMSE of 9.3 knots) outperform the benchmark model (with a RMSE of 13.62 knots). We provide a thorough discussion of our solution approach, including an explanantion of the AlexNet's performance using gradient class activation maps (grad-CAM). Our proposed solution strategy allows future experimentation with various deep learning models in both single and multi-channel settings.

In today's digital age, the internet is essential for communication and the sharing of information, creating a critical need for sophisticated data security measures to prevent unauthorized access and exploitation. Cryptography encrypts messages into a cipher text that is incomprehensible to unauthorized readers, thus safeguarding data during its transmission. Steganography, on the other hand, originates from the Greek term for "covered writing" and involves the art of hiding data within another medium, thereby facilitating covert communication by making the message invisible. This proposed approach takes advantage of the latest advancements in Artificial Intelligence (AI) and Deep Learning (DL), especially through the application of Generative Adversarial Networks (GANs), to improve upon traditional steganographic methods. By embedding encrypted data within another medium, our method ensures that the communication remains hidden from prying eyes. The application of GANs enables a smart, secure system that utilizes the inherent sensitivity of neural networks to slight alterations in data, enhancing the protection against detection. By merging the encryption techniques of cryptography with the hiding capabilities of steganography, and augmenting these with the strengths of AI, we introduce a comprehensive security system designed to maintain both the privacy and integrity of information. This system is crafted not just to prevent unauthorized access or modification of data, but also to keep the existence of the data hidden. This fusion of technologies tackles the core challenges of data security in the current era of open digital communication, presenting an advanced solution with the potential to transform the landscape of information security., Comment: This report pertains to the Capstone Project done by Group 3 of the Fall batch of 2023 students at Praxis Tech School, Kolkata, India. The reports consists of 36 pages and it includes 11 figures and 5 tables

We present an embodied AI system which receives open-ended natural language instructions from a human, and controls two arms to collaboratively accomplish potentially long-horizon tasks over a large workspace. Our system is modular: it deploys state of the art Large Language Models for task planning,Vision-Language models for semantic perception, and Point Cloud transformers for grasping. With semantic and physical safety in mind, these modules are interfaced with a real-time trajectory optimizer and a compliant tracking controller to enable human-robot proximity. We demonstrate performance for the following tasks: bi-arm sorting, bottle opening, and trash disposal tasks. These are done zero-shot where the models used have not been trained with any real world data from this bi-arm robot, scenes or workspace. Composing both learning- and non-learning-based components in a modular fashion with interpretable inputs and outputs allows the user to easily debug points of failures and fragilities. One may also in-place swap modules to improve the robustness of the overall platform, for instance with imitation-learned policies. Please see https://sites.google.com/corp/view/safe-robots .

The field of 3D reconstruction from images has rapidly evolved in the past few years, first with the introduction of Neural Radiance Field (NeRF) and more recently with 3D Gaussian Splatting (3DGS). The latter provides a significant edge over NeRF in terms of the training and inference speed, as well as the reconstruction quality. Although 3DGS works well for dense input images, the unstructured point-cloud like representation quickly overfits to the more challenging setup of extremely sparse input images (e.g., 3 images), creating a representation that appears as a jumble of needles from novel views. To address this issue, we propose regularized optimization and depth-based initialization. Our key idea is to introduce a structured Gaussian representation that can be controlled in 2D image space. We then constraint the Gaussians, in particular their position, and prevent them from moving independently during optimization. Specifically, we introduce single and multiview constraints through an implicit convolutional decoder and a total variation loss, respectively. With the coherency introduced to the Gaussians, we further constrain the optimization through a flow-based loss function. To support our regularized optimization, we propose an approach to initialize the Gaussians using monocular depth estimates at each input view. We demonstrate significant improvements compared to the state-of-the-art sparse-view NeRF-based approaches on a variety of scenes., Comment: Project page: https://people.engr.tamu.edu/nimak/Papers/CoherentGS

Digital signatures are one of the simplest cryptographic building blocks that provide appealing security characteristics such as authenticity, unforgeability, and undeniability. In 1984, Shamir developed the first Identity-based signature (IBS) to simplify public key infrastructure and circumvent the need for certificates. It makes the process uncomplicated by enabling users to verify digital signatures using only the identifiers of signers, such as email, phone number, etc. Nearly all existing IBS protocols rely on several theoretical assumption-based hard problems. Unfortunately, these hard problems are unsafe and pose a hazard in the quantum realm. Thus, designing IBS algorithms that can withstand quantum attacks and ensure long-term security is an important direction for future research. Quantum cryptography (QC) is one such approach. In this paper, we propose an IBS based on QC. Our scheme's security is based on the laws of quantum mechanics. It thereby achieves long-term security and provides resistance against quantum attacks. We verify the proposed design's correctness and feasibility by simulating it in a prototype quantum device and the IBM Qiskit quantum simulator. The implementation code in qiskit with Jupyternotebook is provided in the Annexure. Moreover, we discuss the application of our design in secure email communication.

Routing algorithms play a crucial role in the efficient transmission of data within computer networks by determining the optimal paths for packet forwarding. This paper presents a comprehensive exploration of routing algorithms, focusing on their fundamental principles, classification, challenges, recent advancements, and practical applications. Beginning with an overview of the significance of routing in modern communication networks, the paper delves into the historical evolution of routing algorithms, tracing their development from early approaches to contemporary techniques. Key categories of routing algorithms, including distance vector, link-state, and path vector algorithms, are examined in detail, along with hybrid approaches that integrate multiple routing paradigms. Common challenges faced by routing algorithms, such as routing loops and scalability issues, are identified, and current research efforts aimed at addressing these challenges are discussed.

A deterministic temporal process can be determined by its trajectory, an element in the product space of (a) initial condition $z_0 \in \mathcal{Z}$ and (b) transition function $f: (\mathcal{Z}, \mathcal{T}) \to \mathcal{Z}$ often influenced by the control of the underlying dynamical system. Existing methods often model the transition function as a differential equation or as a recurrent neural network. Despite their effectiveness in predicting future measurements, few results have successfully established a method for sampling and statistical inference of trajectories using neural networks, partially due to constraints in the parameterization. In this work, we introduce a mechanism to learn the distribution of trajectories by parameterizing the transition function $f$ explicitly as an element in a function space. Our framework allows efficient synthesis of novel trajectories, while also directly providing a convenient tool for inference, i.e., uncertainty estimation, likelihood evaluations and out of distribution detection for abnormal trajectories. These capabilities can have implications for various downstream tasks, e.g., simulation and evaluation for reinforcement learning.

Legal research is a crucial task in the practice of law. It requires intense human effort and intellectual prudence to research a legal case and prepare arguments. Recent boom in generative AI has not translated to proportionate rise in impactful legal applications, because of low trustworthiness and and the scarcity of specialized datasets for training Large Language Models (LLMs). This position paper explores the potential of LLMs within Legal Text Analytics (LTA), highlighting specific areas where the integration of human expertise can significantly enhance their performance to match that of experts. We introduce a novel dataset and describe a human centered, compound AI system that principally incorporates human inputs for performing LTA tasks with LLMs., Comment: 7 pages, 7 figures

In this paper, we present FogGuard, a novel fog-aware object detection network designed to address the challenges posed by foggy weather conditions. Autonomous driving systems heavily rely on accurate object detection algorithms, but adverse weather conditions can significantly impact the reliability of deep neural networks (DNNs). Existing approaches include image enhancement techniques like IA-YOLO and domain adaptation methods. While image enhancement aims to generate clear images from foggy ones, which is more challenging than object detection in foggy images, domain adaptation does not require labeled data in the target domain. Our approach involves fine-tuning on a specific dataset to address these challenges efficiently. FogGuard compensates for foggy conditions in the scene, ensuring robust performance by incorporating YOLOv3 as the baseline algorithm and introducing a unique Teacher-Student Perceptual loss for accurate object detection in foggy environments. Through comprehensive evaluations on standard datasets like PASCAL VOC and RTTS, our network significantly improves performance, achieving a 69.43\% mAP compared to YOLOv3's 57.78\% on the RTTS dataset. Additionally, we demonstrate that while our training method slightly increases time complexity, it doesn't add overhead during inference compared to the regular YOLO network., Comment: 8 pages, 1 figures, submitted on Robotic and Automation Letters

GEneral Matrix Multiply (GEMM) is a central operation in deep learning and corresponds to the largest chunk of the compute footprint. Therefore, improving its efficiency is an active topic of ongoing research. A popular strategy is the use of low bit-width integers to approximate the original entries in a matrix. This allows efficiency gains, but often requires sophisticated techniques to control the rounding error incurred. In this work, we first verify/check that when the low bit-width restriction is removed, for a variety of Transformer-based models, whether integers are sufficient for all GEMMs need -- for {\em both} training and inference stages, and can achieve parity with floating point counterparts. No sophisticated techniques are needed. We find that while a large majority of entries in matrices (encountered in such models) can be easily represented by {\em low} bit-width integers, the existence of a few heavy hitter entries make it difficult to achieve efficiency gains via the exclusive use of low bit-width GEMMs alone. To address this issue, we develop a simple algorithm, Integer Matrix Unpacking (IM-Unpack), to {\em unpack} a matrix with large integer entries into a larger matrix whose entries all lie within the representable range of arbitrarily low bit-width integers. This allows {\em equivalence} with the original GEMM, i.e., the exact result can be obtained using purely low bit-width integer GEMMs. This comes at the cost of additional operations -- we show that for many popular models, this overhead is quite small.

The ubiquity and energy needs of industrial refrigeration has prompted several research studies investigating various control opportunities for reducing energy demand. This work focuses on one such opportunity, termed compressor sequencing, which entails intelligently selecting the operational state of the compressors to service the required refrigeration load with the least possible work. We first study the static compressor sequencing problem and observe that deriving the optimal compressor operational state is computationally challenging and can vary dramatically based on the refrigeration load. Thus we introduce load shifting in conjunction with compressor sequencing, which entails strategically precooling the facility to allow for more efficient compressor operation. Interestingly, we show that load shifting not only provides benefits in computing the optimal compressor operational state, but also can lead to significant energy savings. Our results are based on and compared to real-world sensor data from an operating industrial refrigeration site of Butterball LLC located in Huntsville, AR, which demonstrated that without load shifting, even optimal compressor operation results in compressors often running at intermediate capacity levels, which can lead to inefficiencies. Through collected data, we demonstrate that a load shifting approach for compressor sequencing has the potential to reduce energy use of the compressors up to 20% compared to optimal sequencing without load shifting.

Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs to human preferences. In practice, multiple responses can exist for a given prompt with varying quality relative to each other. With availability of such quality ratings for multiple responses, we propose utilizing these responses to create multiple preference pairs for a given prompt. Our work focuses on systematically using the constructed multiple preference pair in DPO training via curriculum learning methodology. In particular, we order these multiple pairs of preference data from easy to hard (emulating curriculum training) according to various criteria. We show detailed comparisons of our proposed approach to the standard single-pair DPO setting. Our method, which we call Curry-DPO consistently shows increased performance gains on MTbench, Vicuna, WizardLM, and the UltraFeedback test set, highlighting its effectiveness. More specifically, Curry-DPO achieves a score of 7.43 on MT-bench with Zephy-7B model outperforming majority of existing LLMs with similar parameter size. Curry-DPO also achieves the highest adjusted win rates on Vicuna, WizardLM, and UltraFeedback test datasets (90.7%, 87.1%, and 87.9% respectively) in our experiments, with notable gains of upto 7.5% when compared to standard DPO technique., Comment: Work in progress

While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to efforts investigating whether CPUs may be viable for inference in routine use in many sectors of the industry. But the imbalance between the compute capabilities of GPUs and CPUs is huge. Motivated by these considerations, we study a module which is a workhorse within modern DNN architectures, GEMM based Feed Forward Networks (FFNs), and assess the extent to which it can be made compute- (or FLOP-) lite. Specifically, we propose an alternative formulation (we call it LookupFFN) to GEMM based FFNs inspired by the recent studies of using Locality Sensitive Hashing (LSH) to approximate FFNs. Our formulation recasts most essential operations as a memory look-up, leveraging the trade-off between the two resources on any platform: compute and memory (since CPUs offer it in abundance). For RoBERTa language model pretraining, our formulation achieves similar performance compared to GEMM based FFNs, while dramatically reducing the required FLOP. Our development is complemented with a detailed hardware profiling of strategies that will maximize efficiency -- not just on contemporary hardware but on products that will be offered in the near/medium term future. Code is avaiable at \url{https://github.com/mlpen/LookupFFN}., Comment: ICML 2023

Transformers are the backbone of powerful foundation models for many Vision and Natural Language Processing tasks. But their compute and memory/storage footprint is large, and so, serving such models is expensive often requiring high-end hardware. To mitigate this difficulty, Post-Training Quantization seeks to modify a pre-trained model and quantize it to eight bits or lower, significantly boosting compute/memory/latency efficiency. Such models have been successfully quantized to four bits with some performance loss. In this work, we outline a simple scheme to quantize Transformer-based models to just two bits (plus some overhead) with only a small drop in accuracy. Key to our formulation is a concept borrowed from Harmonic analysis called Fusion Frames. Our main finding is that the quantization must take place not in the original weight space, but instead in the Fusion Frame representations. If quantization is interpreted as the addition of noise, our casting of the problem allows invoking an extensive body of known consistent recovery and noise robustness guarantees. Further, if desired, de-noising filters are known in closed form. We show empirically, via a variety of experiments, that (almost) two-bit quantization for Transformer models promises sizable efficiency gains. The code is available at https://github.com/vsingh-group/FrameQuant, Comment: 25 pages, 15 figures

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement method using a complex convolutional neural network with an encoder-decoder architecture and a complex multi-head attention transformer. The model is trained to estimate individual complex ratio masks in the time-frequency domain for the left and right-ear channels of binaural hearing devices. The model is trained using a novel loss function that incorporates the preservation of spatial information along with speech intelligibility improvement and noise reduction. Simulation results for acoustic scenarios with a single target speaker and isotropic noise of various types show that the proposed method improves the estimated binaural speech intelligibility and preserves the binaural cues better in comparison with several baseline algorithms., Comment: Accepted to ICASSP 2024

Understanding the modus operandi of adversaries aids organizations in employing efficient defensive strategies and sharing intelligence in the community. This knowledge is often present in unstructured natural language text within threat analysis reports. A translation tool is needed to interpret the modus operandi explained in the sentences of the threat report and translate it into a structured format. This research introduces a methodology named TTPXHunter for the automated extraction of threat intelligence in terms of Tactics, Techniques, and Procedures (TTPs) from finished cyber threat reports. It leverages cyber domain-specific state-of-the-art natural language processing (NLP) to augment sentences for minority class TTPs and refine pinpointing the TTPs in threat analysis reports significantly. The knowledge of threat intelligence in terms of TTPs is essential for comprehensively understanding cyber threats and enhancing detection and mitigation strategies. We create two datasets: an augmented sentence-TTP dataset of 39,296 samples and a 149 real-world cyber threat intelligence report-to-TTP dataset. Further, we evaluate TTPXHunter on the augmented sentence dataset and the cyber threat reports. The TTPXHunter achieves the highest performance of 92.42% f1-score on the augmented dataset, and it also outperforms existing state-of-the-art solutions in TTP extraction by achieving an f1-score of 97.09% when evaluated over the report dataset. TTPXHunter significantly improves cybersecurity threat intelligence by offering quick, actionable insights into attacker behaviors. This advancement automates threat intelligence analysis, providing a crucial tool for cybersecurity professionals fighting cyber threats., Comment: Under Review