Search

The Josephson diode effect (JDE), characterized by a unidirectional supercurrent across a Josephson junction, arises from non-reciprocal critical currents typically controlled by magnetic fields. In this study, we demonstrate JDE controlled by local electric fields, achieving complete polarity reversal through gate voltages on epitaxial Al-InAs Josephson junctions. Our observations reveal intricate effects of in-plane magnetic fields and gate voltages on the JDE. We develop a theoretical model that considers the coherent interplay between finite Cooper-pair momentum (fCPM) and anisotropic spin-orbit coupling (SOC), identifying that fCPM dominates JDE at low in-plane magnetic fields, while SOC governs its polarity reversal at high fields. This model aligns well with experimental data, illustrating precise electric control of JDE polarity through anisotropic SOC. These findings introduce a novel approach to controlling superconducting circuits, paving a route toward advanced applications in superconducting quantum devices., Comment: 42 pages, 19 figures, 1 table

$\text{RuO}_2$, a transition metal oxide, is attracting attention in spintronics for its unique altermagnetic properties, which influence spin currents. Its ability to produce large spin-orbit torques and spin Hall effects is key for energy-efficient magnetic memory and logic devices. Additionally, the tunable thickness and crystallinity of $\text{RuO}_2$ thin films optimize torque efficiency for low-power switching. Spin pumping, a versatile method for investigating spin dynamics in $\text{RuO}_2$ thin films, has garnered considerable interest because of its straightforward, non-invasive and uncomplicated approach to addressing impedance mismatch and direct measurement of spintronic parameters. Here we present a systematic and detailed analysis on the efficient spin to charge conversion in (110)-oriented $\text{RuO}_2$ films with amorphous CoFeB as spin source. The spin Hall angle, and spin diffusion length were estimated to be 0.14 $\pm$ 0.01 and 4.58 $\pm$ 0.40 nm, respectively. The spin Hall conductivity of 998.89 $\pm$ 58.23 $\hbar \cdot \frac{\Omega^{-1} \, \text{cm}^{-1}}{e}$ has been estimated which is theoretically predicted to be of the similar order. The interfacial spin transparency has been achieved to be 90%. We have shown that the spin memory loss at the $\text{RuO}_2$/CoFeB interface is 15%, which is very small.

This work presents the design and development of IIT Bombay Racing's Formula Student style autonomous racecar algorithm capable of running at the racing events of Formula Student-AI, held in the UK. The car employs a cutting-edge sensor suite of the compute unit NVIDIA Jetson Orin AGX, 2 ZED2i stereo cameras, 1 Velodyne Puck VLP16 LiDAR and SBG Systems Ellipse N GNSS/INS IMU. It features deep learning algorithms and control systems to navigate complex tracks and execute maneuvers without any human intervention. The design process involved extensive simulations and testing to optimize the vehicle's performance and ensure its safety. The algorithms have been tested on a small scale, in-house manufactured 4-wheeled robot and on simulation software. The results obtained for testing various algorithms in perception, simultaneous localization and mapping, path planning and controls have been detailed., Comment: 8 pages, 19 figures

Topology and superconductivity, two distinct phenomena offer unique insight into quantum properties and their applications in quantum technologies, spintronics, and sustainable energy technologies if system can be found where they coexist. Tin (Sn) plays a pivotal role here as an element due to its two structural phases, $\alpha$-Sn and $\beta$-Sn, exhibiting topological characteristics ($\alpha$-Sn) and superconductivity ($\beta$-Sn). In this study we show how precise control of $\alpha$ and $\beta$ phases of Sn thin films can be achieved by using molecular beam epitaxy grown buffer layers with systematic control over the lattice parameter. The resulting Sn films showed either $\beta$-Sn or $\alpha$-Sn phases as the lattice constant of the buffer layer was varied from 6.10 A to 6.48 A, covering the range between GaSb (closely matched to InAs) and InSb. The crystal structures of the $\alpha$- and $\beta$-Sn films were characterized by x-ray diffraction and confirmed by Raman spectroscopy and scanning transmission electron microscopy. The smooth and continuous surface morphology of the Sn films was validated using atomic force microscopy. The characteristics of $\alpha$- and $\beta$-Sn phases were further verified using electrical transport measurements by observing resistance drop near 3.7 K for superconductivity of the $\beta$-Sn phase and Shubnikov-de Haas oscillations for the $\alpha$-Sn phase. Density functional theory calculations showed that the stability of the Sn phases is highly dependent on lattice strain, with $\alpha$-Sn being more stable under tensile strain and $\beta$-Sn becoming favorable under compressive strain, which is in good agreement with experimental observations. Hence, this study sheds light on controlling Sn phases through lattice engineering, enabling innovative applications in quantum technologies and beyond.

Kernel ridge regression (KRR) is a fundamental computational tool, appearing in problems that range from computational chemistry to health analytics, with a particular interest due to its starring role in Gaussian process regression. However, it is challenging to scale KRR solvers to large datasets: with $n$ training points, a direct solver (i.e., Cholesky decomposition) uses $O(n^2)$ storage and $O(n^3)$ flops. Iterative methods for KRR, such as preconditioned conjugate gradient (PCG), avoid the cubic scaling of direct solvers and often use low-rank preconditioners; a rank $r$ preconditioner uses $O(rn)$ storage and each iteration requires $O(n^2)$ flops. To reduce the storage and iteration complexity of iterative solvers for KRR, we propose ASkotch ($\textbf{A}$ccelerated $\textbf{s}$calable $\textbf{k}$ernel $\textbf{o}$p$\textbf{t}$imization using block $\textbf{c}$oordinate descent with $\textbf{H}$essian preconditioning). For a given block size $|b| << n$, each iteration of ASkotch uses $O(r|b| + n)$ storage and $O(n|b|)$ flops, so ASkotch scales better than Cholesky decomposition and PCG. We prove that ASkotch obtains linear convergence to the optimum, with the convergence rate depending on the square roots of the $\textit{preconditioned}$ block condition numbers. Furthermore, we solve KRR problems that were considered to be impossibly large while using limited computational resources: we show that ASkotch outperforms PCG methods with respect to generalization error on large-scale KRR (up to $n = 10^8$) and KRR classification tasks (up to $n = 10^7$) while running each of our experiments on $\textit{a single 12 GB Titan V GPU}$. Our work opens up the possibility of as-yet-unimagined applications of KRR across a wide range of disciplines., Comment: 40 pages (including appendices), 14 figures, 3 tables

The application of quantum algorithms to classical problems is generally accompanied by significant bottlenecks when transferring data between quantum and classical states, often negating any intrinsic quantum advantage. Here we address this challenge for a well-known algorithm for linear systems of equations, originally proposed by Harrow, Hassidim and Lloyd (HHL), by adapting it into a predictor-corrector instead of a direct solver. Rather than seeking the solution at the next time step, the goal now becomes determining the change between time steps. This strategy enables the intelligent omission of computationally costly steps commonly found in many classical algorithms, while simultaneously mitigating the notorious readout problems associated with extracting solutions from a quantum state. Random or regularly performed skips instead lead to simulation failure. We demonstrate that our methodology secures a useful polynomial advantage over a conventional application of the HHL algorithm. The practicality and versatility of the approach are illustrated through applications in various fields such as smoothed particle hydrodynamics, plasma simulations, and reactive flow configurations. Moreover, the proposed algorithm is well suited to run asynchronously on future heterogeneous hardware infrastructures and can effectively leverage the synergistic strengths of classical as well as quantum compute resources.

Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other languages is still underexplored. We investigate their effectiveness for NLP tasks in low-resource languages (LRLs), especially in the setting of zero-labelled cross-lingual transfer (0-CLT), where no labelled training data for the target language is available -- however training data from one or more related medium-resource languages (MRLs) is utilized, alongside the available unlabeled test data for a target language. We introduce Self-Supervised Prompting (SSP), a novel ICL approach tailored for the 0-CLT setting. SSP is based on the key observation that LLMs output more accurate labels if in-context exemplars are from the target language (even if their labels are slightly noisy). To operationalize this, since target language training data is not available in 0-CLT, SSP operates in two stages. In Stage I, using source MRL training data, target language's test data is noisily labeled. In Stage II, these noisy test data points are used as exemplars in ICL for further improved labelling. Additionally, our implementation of SSP uses a novel Integer Linear Programming (ILP)-based exemplar selection that balances similarity, prediction confidence (when available) and label coverage. Experiments on three tasks and eleven LRLs (from three regions) demonstrate that SSP strongly outperforms existing SOTA fine-tuned and prompting-based baselines in 0-CLT setup.

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.

In this brief note we calculate the entanglement entropy in $M^{\otimes N}/S_N$ symmetric orbifold CFTs in the presence of topological defects, which were recently constructed in \cite{Gutperle:2024vyp,Knighton:2024noc}. We consider both universal defects which realize $Rep(S_N)$ non-invertible symmetry and non-universal defects. We calculate the sub-leading defect entropy/g-factor for defects at the boundary entangling surface as well as inside it., Comment: 16 pages, 5 figures

In this work, we delve into the EEG classification task in the domain of visual brain decoding via two frameworks, involving two different learning paradigms. Considering the spatio-temporal nature of EEG data, one of our frameworks is based on a CNN-BiLSTM model. The other involves a CNN-Transformer architecture which inherently involves the more versatile attention based learning paradigm. In both cases, a special 1D-CNN feature extraction module is used to generate the initial embeddings with 1D convolutions in the time and the EEG channel domains. Considering the EEG signals are noisy, non stationary and the discriminative features are even less clear (than in semantically structured data such as text or image), we also follow a window-based classification followed by majority voting during inference, to yield labels at a signal level. To illustrate how brain patterns correlate with different image classes, we visualize t-SNE plots of the BiLSTM embeddings alongside brain activation maps for the top 10 classes. These visualizations provide insightful revelations into the distinct neural signatures associated with each visual category, showcasing the BiLSTM's capability to capture and represent the discriminative brain activity linked to visual stimuli. We demonstrate the performance of our approach on the updated EEG-Imagenet dataset with positive comparisons with state-of-the-art methods., Comment: The paper has been submitted at ICPR 2024. It contains 17 pages with 9 images

We study non-invertible defects in two-dimensional $S_N$ orbifold CFTs. We construct universal defects which do not depend on the details of the seed CFT and hence exist in any orbifold CFT. Additionally, we investigate non-universal defects arising from the topological defects of the seed CFT. We argue that there exist universal defects that are non-trivial in the large-$N$ limit, making them relevant for the AdS$_3$/CFT$_2$ correspondence. We then focus on AdS$_3\times$S$^3\times \mathcal M_4$ with one unit of NS-NS flux and propose an explicit realization of these defects on the worldsheet.

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.

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.

The Handwritten Text Recognition problem has been a challenge for researchers for the last few decades, especially in the domain of computer vision, a subdomain of pattern recognition. Variability of texts amongst writers, cursiveness, and different font styles of handwritten texts with degradation of historical text images make it a challenging problem. Recognizing scanned document images in neural network-based systems typically involves a two-step approach: segmentation and recognition. However, this method has several drawbacks. These shortcomings encompass challenges in identifying text regions, analyzing layout diversity within pages, and establishing accurate ground truth segmentation. Consequently, these processes are prone to errors, leading to bottlenecks in achieving high recognition accuracies. Thus, in this study, we present an end-to-end paragraph recognition system that incorporates internal line segmentation and gated convolutional layers based encoder. The gating is a mechanism that controls the flow of information and allows to adaptively selection of the more relevant features in handwritten text recognition models. The attention module plays an important role in performing internal line segmentation, allowing the page to be processed line-by-line. During the decoding step, we have integrated a connectionist temporal classification-based word beam search decoder as a post-processing step. In this work, we have extended existing LexiconNet by carefully applying and utilizing gated convolutional layers in the existing deep neural network. Our results at line and page levels also favour our new GatedLexiconNet. This study reported character error rates of 2.27% on IAM, 0.9% on RIMES, and 2.13% on READ-16, and word error rates of 5.73% on IAM, 2.76% on RIMES, and 6.52% on READ-2016 datasets.

This study investigated the use of portable X-ray fluorescence (PXRF) spectrometry and soil image analysis for rapid soil fertility assessment, with a focus on key indicators such as available boron (B), organic carbon (OC), available manganese (Mn), available sulfur (S), and the sulfur availability index (SAI). A total of 1,133 soil samples from diverse agro-climatic zones in Eastern India were analyzed. The research integrated color and texture features from microscopic soil images, PXRF data, and auxiliary soil variables (AVs) using a Random Forest model. Results showed that combining image features (IFs) with AVs significantly improved prediction accuracy for available B (R2 = 0.80) and OC (R2 = 0.88). A data fusion approach, incorporating IFs, AVs, and PXRF data, further enhanced predictions for available Mn and SAI, with R2 values of 0.72 and 0.70, respectively. The study highlights the potential of integrating these technologies to offer rapid, cost-effective soil testing methods, paving the way for more advanced predictive models and a deeper understanding of soil fertility. Future work should explore the application of deep learning models on a larger dataset, incorporating soils from a wider range of agro-climatic zones under field conditions., Comment: Published in 'Soil Advances'

The paper presents a novel Auto Language Prediction Dictionary Capsule (ALPDC) framework for language prediction and machine translation. The model uses a combination of neural networks and symbolic representations to predict the language of a given input text and then translate it to a target language using pre-built dictionaries. This research work also aims to translate the text of various languages to its literal meaning in English. The proposed model achieves state-of-the-art results on several benchmark datasets and significantly improves translation accuracy compared to existing methods. The results show the potential of the proposed method for practical use in multilingual communication and natural language processing tasks., Comment: 21 Pages

With the advent of exascale computing, effective load balancing in massively parallel software applications is critically important for leveraging the full potential of high performance computing systems. Load balancing is the distribution of computational work between available processors. Here, we investigate the application of quantum annealing to load balance two paradigmatic algorithms in high performance computing. Namely, adaptive mesh refinement and smoothed particle hydrodynamics are chosen as representative grid and off-grid target applications. While the methodology for obtaining real simulation data to partition is application specific, the proposed balancing protocol itself remains completely general. In a grid based context, quantum annealing is found to outperform classical methods such as the round robin protocol but lacks a decisive advantage over more advanced methods such as steepest descent or simulated annealing despite remaining competitive. The primary obstacle to scalability is found to be limited coupling on current quantum annealing hardware. However, for the more complex particle formulation, approached as a multi-objective optimization, quantum annealing solutions are demonstrably Pareto dominant to state of the art classical methods across both objectives. This signals a noteworthy advancement in solution quality which can have a large impact on effective CPU usage.

Spin pumping has significant implications for spintronics, providing a mechanism to manipulate and transport spins for information processing. Understanding and harnessing spin currents through spin pumping is critical for the development of efficient spintronic devices. The use of a magnetic insulator with low damping, enhances the signal-to-noise ratio in crucial experiments such as spin-torque ferromagnetic resonance (FMR) and spin pumping. A magnetic insulator coupled with a heavy metal or quantum material offers a more straight forward model system, especially when investigating spin-charge interconversion processes to greater accuracy. This simplicity arises from the absence of unwanted effects caused by conduction electrons unlike in ferromagnetic metals. Here, we investigate the spin pumping in coupled ferrimagnetic (FiM) Y3Fe5O12 (YIG)/Tm3Fe5O12 (TmIG) bilayers combined with heavy-metal (Pt) using the inverse spin Hall effect (ISHE). It is observed that magnon transmission occurs at both of the FiMs FMR positions. The enhancement of spin pumping voltage (Vsp) in the FiM garnet heterostructures is attributed to the strong interfacial exchange coupling between FiMs. The modulation of Vsp is achieved by tuning the bilayer structure. Further, the spin mixing conductance for these coupled systems is found to be 10^18 m^-2. Our findings describe a novel coupled FiM system for the investigation of magnon coupling providing new prospects for magnonic devices.

This paper explores challenges in training Physics-Informed Neural Networks (PINNs), emphasizing the role of the loss landscape in the training process. We examine difficulties in minimizing the PINN loss function, particularly due to ill-conditioning caused by differential operators in the residual term. We compare gradient-based optimizers Adam, L-BFGS, and their combination Adam+L-BFGS, showing the superiority of Adam+L-BFGS, and introduce a novel second-order optimizer, NysNewton-CG (NNCG), which significantly improves PINN performance. Theoretically, our work elucidates the connection between ill-conditioned differential operators and ill-conditioning in the PINN loss and shows the benefits of combining first- and second-order optimization methods. Our work presents valuable insights and more powerful optimization strategies for training PINNs, which could improve the utility of PINNs for solving difficult partial differential equations., Comment: ICML 2024 Oral; 33 pages (including appendices), 10 figures, 3 tables

Thermalization of a system when interacting with a thermal bath is an interesting problem. If a system eventually reaches a thermal state in the long time limit, it's expected that its density matrix would resemble the mean-force Gibbs state. Moreover, the correlation function must satisfy the Kubo-Martin-Schwinger (KMS) condition or equivalently the Fluctuation-Dissipation Relation (FDR). In this paper, we derive a formal expression for the non-Markovian two-point function within the context of the weak coupling limit. Using this expression, we explicitly compute the two-point function for specific models, demonstrating their adherence to the KMS. In addition, we have formulated a non-perturbative approach in the form of a self-consistent approximation that includes a partial resummation of perturbation theory. This approach can capture strong coupling phenomena while still relying on simple equations. Notably, we verify that the two-point function obtained through this method also satisfies the KMS condition., Comment: 16 pages, 5 Figures

Quantum computing promises to provide the next step up in computational power for diverse application areas. In this review, we examine the science behind the quantum hype, and the breakthroughs required to achieve true quantum advantage in real world applications. Areas that are likely to have the greatest impact on high performance computing (HPC) include simulation of quantum systems, optimization, and machine learning. We draw our examples from electronic structure calculations and computational fluid dynamics which account for a large fraction of current scientific and engineering use of HPC. Potential challenges include encoding and decoding classical data for quantum devices, and mismatched clock speeds between classical and quantum processors. Even a modest quantum enhancement to current classical techniques would have far-reaching impacts in areas such as weather forecasting, engineering, aerospace, drug design, and the design of "green" materials for sustainable development. This requires significant effort from the computational science, engineering and quantum computing communities working together., Comment: review paper, 43 pages + 28 pages references

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. Traditionally, convolutional neural networks (CNNs) dominated this domain, excelling at local feature extraction. However, their limitations in capturing long-range dependencies across image regions pose challenges for segmenting complex, interconnected structures often encountered in medical data. In recent years, Vision Transformers (ViTs) have emerged as a promising technique for addressing the challenges in medical image segmentation. Their multi-scale attention mechanism enables effective modeling of long-range dependencies between distant structures, crucial for segmenting organs or lesions spanning the image. Additionally, ViTs' ability to discern subtle pattern heterogeneity allows for the precise delineation of intricate boundaries and edges, a critical aspect of accurate medical image segmentation. However, they do lack image-related inductive bias and translational invariance, potentially impacting their performance. Recently, researchers have come up with various ViT-based approaches that incorporate CNNs in their architectures, known as Hybrid Vision Transformers (HVTs) to capture local correlation in addition to the global information in the images. This survey paper provides a detailed review of the recent advancements in ViTs and HVTs for medical image segmentation. Along with the categorization of ViT and HVT-based medical image segmentation approaches, we also present a detailed overview of their real-time applications in several medical image modalities. This survey may serve as a valuable resource for researchers, healthcare practitioners, and students in understanding the state-of-the-art approaches for ViT-based medical image segmentation.

In August 2023, more than 30 students joined the Special Remote DESY summer-school to work on projects of importance for LHC experiments. In a dedicated initiative, analyses that had not been incorporated into the RIVET package were implemented and verified. Here, a brief description of the accomplished work is given, and a comparison of the measurements with predictions obtained from matched standard parton shower Monte Carlo event generators as well as with those obtained from Parton-Branching TMDs with corresponding parton showers are presented.

In this paper, we present an efficient solution for weed classification in agriculture. We focus on optimizing model performance at inference while respecting the constraints of the agricultural domain. We propose a Quantized Deep Neural Network model that classifies a dataset of 9 weed classes using 8-bit integer (int8) quantization, a departure from standard 32-bit floating point (fp32) models. Recognizing the hardware resource limitations in agriculture, our model balances model size, inference time, and accuracy, aligning with practical requirements. We evaluate the approach on ResNet-50 and InceptionV3 architectures, comparing their performance against their int8 quantized versions. Transfer learning and fine-tuning are applied using the DeepWeeds dataset. The results show staggering model size and inference time reductions while maintaining accuracy in real-world production scenarios like Desktop, Mobile and Raspberry Pi. Our work sheds light on a promising direction for efficient AI in agriculture, holding potential for broader applications. Code: https://github.com/parikshit14/QNN-for-weed, Comment: 6 pages, 6 figures, 4 tables

We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the target LA or LA of another related language. Training target LA requires unlabeled data, which may not be readily available for low resource unseen languages: those that are neither seen by the underlying multilingual language model (e.g., mBERT), nor do we have any (labeled or unlabeled) data for them. We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL. Extensive experimentation across four language groups, covering 15 unseen target languages, demonstrates improvements of up to 3.2 average F1 points over standard fine-tuning and other strong baselines on POS tagging and NER tasks. We also extend ZGUL to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language. We find that ZGUL continues to outperform baselines in these settings too.

The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a lower-dimensional space, which is crucial for effective data representation. To address this limitation, we propose a novel approach called Low-Rank Autoencoder (LoRAE). In LoRAE, we incorporated a low-rank regularizer to adaptively reconstruct a low-dimensional latent space while preserving the basic objective of an autoencoder. This helps embed the data in a lower-dimensional space while preserving important information. It is a simple autoencoder extension that learns low-rank latent space. Theoretically, we establish a tighter error bound for our model. Empirically, our model's superiority shines through various tasks such as image generation and downstream classification. Both theoretical and practical outcomes highlight the importance of acquiring low-dimensional embeddings., Comment: Accepted @ IEEE/CVF WACV 2024