Search

This work discusses the problem of optimal excitation of a three-level atom of ladder-configuration by light in the two-photon state and coherent light carrying an average of two photons. The applied atom-light interaction model is based on the Wigner-Weisskopf approximation. We characterize the properties of the optimal two-photon state that excites an atom perfectly, i.e. with probability equal to one: We find that the spectro-temporal shape of the optimal state of light is determined by the lifetimes of the atomic states, with the degree of photonic entanglement in the optimal state depends on the lifetime ratio. In consequence, two distinct interaction regimes can be identified in which the entanglement of the input state of light has qualitatively different impact. As the optimal states may be challenging to prepare in general, we compare the results with those obtained for photon pairs of selected experimentally-relevant pulse shapes. As these shapes are optimized for maximal atomic excitation probability, the results can be interpreted in terms of the overlap between the optimal and investigated pulse shapes., Comment: 16 pages, 14 figures

Satirical news is real news combined with a humorous comment or exaggerated content, and it often mimics the format and style of real news. However, satirical news is often misunderstood as misinformation, especially by individuals from different cultural and social backgrounds. This research addresses the challenge of distinguishing satire from truthful news by leveraging multilingual satire detection methods in English and Arabic. We explore both zero-shot and chain-of-thought (CoT) prompting using two language models, Jais-chat(13B) and LLaMA-2-chat(7B). Our results show that CoT prompting offers a significant advantage for the Jais-chat model over the LLaMA-2-chat model. Specifically, Jais-chat achieved the best performance, with an F1-score of 80\% in English when using CoT prompting. These results highlight the importance of structured reasoning in CoT, which enhances contextual understanding and is vital for complex tasks like satire detection., Comment: ALTA 2024 (Selected for publication)

The use of Large Language Models (LLMs) in software development is rapidly growing, with developers increasingly relying on these models for coding assistance, including security-critical tasks. Our work presents a comprehensive comparison between traditional static analysis tools for cryptographic API misuse detection-CryptoGuard, CogniCrypt, and Snyk Code-and the LLMs-GPT and Gemini. Using benchmark datasets (OWASP, CryptoAPI, and MASC), we evaluate the effectiveness of each tool in identifying cryptographic misuses. Our findings show that GPT 4-o-mini surpasses current state-of-the-art static analysis tools on the CryptoAPI and MASC datasets, though it lags on the OWASP dataset. Additionally, we assess the quality of LLM responses to determine which models provide actionable and accurate advice, giving developers insights into their practical utility for secure coding. This study highlights the comparative strengths and limitations of static analysis versus LLM-driven approaches, offering valuable insights into the evolving role of AI in advancing software security practices.

Lorentz invariance violation (LIV) is a topic of significant interest in quantum gravity and in extensions of the Standard Model of particle physics. Recently, new classes of black hole solutions have been proposed, involving vector fields and rank-two antisymmetric tensor fields that acquire nontrivial vacuum expectation values, resulting in the Bumblebee and Kalb-Ramond (KR) gravity models, respectively. These models exhibit novel geometric structures and differ in notable ways from standard Einstein gravity. In this study, we examine neutral anti-de Sitter (AdS) black holes within the context of LIV backgrounds, focusing on their thermodynamic properties through two distinct approaches. The first approach utilizes the free energy landscape framework, revealing substantial modifications to the conventional Hawking-Page phase transition. Specifically, LIV effects can alter the stability regimes of black holes and thermal AdS phases, potentially leading to overlapping thermodynamic regimes that would otherwise remain distinct. The second approach involves thermodynamic Ruppeiner geometry, which provides a window into the microstructure of black holes via a well-defined scalar curvature. In general, LIV effects are negligible for larger black holes, which behave like an ideal gas with no significant interactions among their constituents. However, at shorter length scales, the presence of LIV can induce multiple stable and unstable phase transitions, depending on the specific gravity model and the magnitude of LIV effects considered. While Bumblebee and Kalb-Ramond gravity share several similarities, we identify distinctive signatures arising from their underlying physical mechanisms. These differences may provide key observational and theoretical constraints for testing LIV effects in black hole physics., Comment: 29 pages, 12 figures

Seismic data inevitably suffers from random noise and missing traces in field acquisition. This limits the utilization of seismic data for subsequent imaging or inversion applications. Recently, dictionary learning has gained remarkable success in seismic data denoising and interpolation. Variants of the patch-based learning technique, such as the K-SVD algorithm, have been shown to improve denoising and interpolation performance compared to the analytic transform-based methods. However, patch-based learning algorithms work on overlapping patches of data and do not take the full data into account during reconstruction. By contrast, the data patches (CSC) model treats signals globally and, therefore, has shown superior performance over patch-based methods in several image processing applications. In consequence, we test the use of CSC model for seismic data denoising and interpolation. In particular, we use the local block coordinate descent (LoBCoD) algorithm to reconstruct missing traces and clean seismic data from noisy input. The denoising and interpolation performance of the LoBCoD algorithm has been compared with that of K-SVD and orthogonal matching pursuit (OMP) algorithms using synthetic and field data examples. We use three quality measures to test the denoising accuracy: the peak signal-to-noise ratio (PSNR), the relative L2-norm of the error (RLNE), and the structural similarity index (SSIM). We find that LoBCoD performs better than K-SVD and OMP for all test cases in improving PSNR and SSIM, and in reducing RLNE. These observations suggest a huge potential of the CSC model in seismic data denoising and interpolation applications., Comment: 56 pages, 19 figures, 7 tables

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning capability on many NLP tasks. Recasting an NLP task into a text-to-text generation task is a common practice so that generative LLMs can be prompted to resolve it. However, performing document-level relation extraction (DocRE) tasks with generative LLM models is still challenging due to the structured output format of DocRE, which complicates the conversion to plain text. Limited information available in few-shot samples and prompt instructions induce further difficulties and challenges in relation extraction for mentioned entities in a document. In this paper, we represent the structured output as a graph-style triplet rather than natural language expressions and leverage generative LLMs for the DocRE task. Our approach, the Graph-DPEP framework is grounded in the reasoning behind triplet explanation thoughts presented in natural language. In this framework, we first introduce a ``decomposed-plug" method for performing the generation from LLMs over prompts with type-space decomposition to alleviate the burden of distinguishing all relation types. Second, we employ a verifier for calibrating the generation and identifying overlooked query entity pairs. Third, we develop "ensemble-play", reapplying generation on the entire type list by leveraging the reasoning thoughts embedded in a sub-graph associated with the missing query pair to address the missingness issue. Through extensive comparisons with existing prompt techniques and alternative Language Models (LLMs), our framework demonstrates superior performance on publicly available benchmarks in experiments.

Identifying an appropriate task space that simplifies control solutions is important for solving robotic manipulation problems. One approach to this problem is learning an appropriate low-dimensional action space. Linear and nonlinear action mapping methods have trade-offs between simplicity on the one hand and the ability to express motor commands outside of a single low-dimensional subspace on the other. We propose that learning local linear action representations that adapt based on the current configuration of the robot achieves both of these benefits. Our state-conditioned linear maps ensure that for any given state, the high-dimensional robotic actuations are linear in the low-dimensional action. As the robot state evolves, so do the action mappings, ensuring the ability to represent motions that are immediately necessary. These local linear representations guarantee desirable theoretical properties by design, and we validate these findings empirically through two user studies. Results suggest state-conditioned linear maps outperform conditional autoencoder and PCA baselines on a pick-and-place task and perform comparably to mode switching in a more complex pouring task., Comment: 7 Pages, 8 Figures, Presented at the 2023 IEEE International Conference on Robotics and Automation (ICRA)

Representation learning has become increasingly important, especially as powerful models have shifted towards learning latent representations before fine-tuning for downstream tasks. This approach is particularly valuable in leveraging the structural information within brain anatomy. However, a common limitation of recent models developed for MRIs is their tendency to ignore or remove geometric information, such as translation and rotation, thereby creating invariance with respect to geometric operations. We contend that incorporating knowledge about these geometric transformations into the model can significantly enhance its ability to learn more detailed anatomical information within brain structures. As a result, we propose a novel method for encoding 3D MRIs that enforces equivariance with respect to all rotations in 3D space, in other words, SO(3)-equivariance (SOE). By explicitly modeling this geometric equivariance in the representation space, we ensure that any rotational operation applied to the input image space is also reflected in the embedding representation space. This approach requires moving beyond traditional representation learning methods, as we need a representation vector space that allows for the application of the same SO(3) operation in that space. To facilitate this, we leverage the concept of vector neurons. The representation space formed by our method captures the brain's structural and anatomical information more effectively. We evaluate SOE pretrained on the structural MRIs of two public data sets with respect to the downstream task of predicting age and diagnosing Alzheimer's Disease from T1-weighted brain scans of the ADNI data set. We demonstrate that our approach not only outperforms other methods but is also robust against various degrees of rotation along different axes. The code is available at https://github.com/shizhehe/SOE-representation-learning.

Transformers have a quadratic scaling of computational complexity with input size, which limits the input context window size of large language models (LLMs) in both training and inference. Meanwhile, retrieval-augmented generation (RAG) besed models can better handle longer contexts by using a retrieval system to filter out unnecessary information. However, most RAG methods only perform retrieval based on the initial query, which may not work well with complex questions that require deeper reasoning. We introduce a novel approach, Inner Loop Memory Augmented Tree Retrieval (ILM-TR), involving inner-loop queries, based not only on the query question itself but also on intermediate findings. At inference time, our model retrieves information from the RAG system, integrating data from lengthy documents at various levels of abstraction. Based on the information retrieved, the LLM generates texts stored in an area named Short-Term Memory (STM) which is then used to formulate the next query. This retrieval process is repeated until the text in STM converged. Our experiments demonstrate that retrieval with STM offers improvements over traditional retrieval-augmented LLMs, particularly in long context tests such as Multi-Needle In A Haystack (M-NIAH) and BABILong.

This paper presents a nested tracking framework for analyzing cycles in 2D force networks within granular materials. These materials are composed of interacting particles, whose interactions are described by a force network. Understanding the cycles within these networks at various scales and their evolution under external loads is crucial, as they significantly contribute to the mechanical and kinematic properties of the system. Our approach involves computing a cycle hierarchy by partitioning the 2D domain into segments bounded by cycles in the force network. We can adapt concepts from nested tracking graphs originally developed for merge trees by leveraging the duality between this partitioning and the cycles. We demonstrate the effectiveness of our method on two force networks derived from experiments with photoelastic disks., Comment: TopoInVis 2024, 11 pages

Despite significant research efforts and advancements, cancer remains a leading cause of mortality. Early cancer prediction has become a crucial focus in cancer research to streamline patient care and improve treatment outcomes. Manual tumor detection by histopathologists can be time consuming, prompting the need for computerized methods to expedite treatment planning. Traditional approaches to tumor detection rely on supervised learning, necessitates a large amount of annotated data for model training. However, acquiring such extensive labeled data can be laborious and time\-intensive. This research examines the three learning environments: supervised learning (SL), semi\-supervised learning (Semi\-SL), and self\-supervised learning (Self\-SL): to predict kidney, lung, and breast cancer. Three pre\-trained deep learning models (Residual Network\-50, Visual Geometry Group\-16, and EfficientNetB0) are evaluated based on these learning settings using seven carefully curated training sets. To create the first training set (TS1), SL is applied to all annotated image samples. Five training sets (TS2\-TS6) with different ratios of labeled and unlabeled cancer images are used to evaluateSemi\-SL. Unlabeled cancer images from the final training set (TS7) are utilized for Self\-SL assessment. Among different learning environments, outcomes from the Semi\-SL setting show a strong degree of agreement with the outcomes achieved in the SL setting. The uniform pattern of observations from the pre\-trained models across all three datasets validates the methodology and techniques of the research. Based on modest number of labeled samples and minimal computing cost, our study suggests that the Semi\-SL option can be a highly viable replacement for the SL option under label annotation constraint scenarios., Comment: Submitted to the journal

The electrocardiogram (ECG) is a ubiquitous diagnostic test. Conventional task-specific ECG analysis models require large numbers of expensive ECG annotations or associated labels to train. Transfer learning techniques have been shown to improve generalization and reduce reliance on labeled data. We present ECG-FM, an open foundation model for ECG analysis, and conduct a comprehensive study performed on a dataset of 1.66 million ECGs sourced from both publicly available and private institutional sources. ECG-FM adopts a transformer-based architecture and is pretrained on 2.5 million samples using ECG-specific augmentations and contrastive learning, as well as a continuous signal masking objective. Our transparent evaluation includes a diverse range of downstream tasks, where we predict ECG interpretation labels, reduced left ventricular ejection fraction, and abnormal cardiac troponin. Affirming ECG-FM's effectiveness as a foundation model, we demonstrate how its command of contextual information results in strong performance, rich pretrained embeddings, and reliable interpretability. Due to a lack of open-weight practices, we highlight how ECG analysis is lagging behind other medical machine learning subfields in terms of foundation model adoption. Our code is available at https://github.com/bowang-lab/ECG-FM/., Comment: 22 pages, 7 figures, 10 tables

This paper presents the design and comprehensive measurements of a compact high-gain 32 element planar antenna array covering the n257 (26.5-29.5 GHz) millimeter wave (mmWave) band. First an 8-element quasi-uniform linear array is designed using a series-fed topology with fan shaped beams for point-to-multipoint connectivity followed by a compact corporate series feed network to design high-gain directive array for point-to-point connectivity. The radiation patterns of both antenna arrays in the azimuth and elevation planes are measured across a 180 degrees span using an over-the-air (OTA) compact antenna test range (CATR) system with a single rotary positioner. Moreover the procedure for quantifying and measuring the gain of mmWave antenna arrays is demonstrated in detail. The peak measured gain of the planar array is 18.45 dBi at 28.5 GHz while the half-power beamwidth of the planar array in the elevation and azimuth planes varies between 11 to 13 degrees, and 23-27 degrees respectively within the 26.5-29.5 GHz range. The measurement results match well with the simulations. The designed antenna array is suitable for various emerging 5G and beyond mmWave applications such as fixed wireless access, mmWave near-field focusing, high-resolution radar systems, and the characterization of mmWave path loss and channel sounding in diverse indoor environments and smart factories., Comment: 11 Pages, 15 Figues, Orignalsubmission

In this work, we propose a set of physics-informed geometric operators (GOs) to enrich the geometric data provided for training surrogate/discriminative models, dimension reduction, and generative models, typically employed for performance prediction, dimension reduction, and creating data-driven parameterisations, respectively. However, as both the input and output streams of these models consist of low-level shape representations, they often fail to capture shape characteristics essential for performance analyses. Therefore, the proposed GOs exploit the differential and integral properties of shapes--accessed through Fourier descriptors, curvature integrals, geometric moments, and their invariants--to infuse high-level intrinsic geometric information and physics into the feature vector used for training, even when employing simple model architectures or low-level parametric descriptions. We showed that for surrogate modelling, along with the inclusion of the notion of physics, GOs enact regularisation to reduce over-fitting and enhance generalisation to new, unseen designs. Furthermore, through extensive experimentation, we demonstrate that for dimension reduction and generative models, incorporating the proposed GOs enriches the training data with compact global and local geometric features. This significantly enhances the quality of the resulting latent space, thereby facilitating the generation of valid and diverse designs. Lastly, we also show that GOs can enable learning parametric sensitivities to a great extent. Consequently, these enhancements accelerate the convergence rate of shape optimisers towards optimal solutions.

Virtual transitions in a Casimir-like configuration are utilized to probe quantum aspects of the recently proposed four-dimensional Einstein-Gauss-Bonnet (4D EGB) gravity. This study employs a quantum optics-based approach, wherein an Unruh-DeWitt detector (modeled as a two-level atom) follows a radial timelike geodesic, falling freely into an uncharged, nonrotating black hole described by 4D EGB gravity, becoming thermalized in the usual Unruh manner. The black hole, asymptotically Minkowskian, is enclosed by a Casimir boundary proximate to its horizon, serving as a source for accelerated field modes that interact with the infalling detector. Observations are conducted by an asymptotic infinity observer, assuming a Boulware field state. Our numerical analysis reveals that, unlike in Einstein gravity, black holes in 4D EGB gravity can either enhance or suppress the intensity of acceleration radiation, contingent upon the Gauss-Bonnet coupling parameter $\alpha$. Specifically, we observe radiation enhancement for negative $\alpha$ and suppression for positive $\alpha$. These findings offer substantial insights into quantifying the influence of higher-curvature contributions on the behavior of quantum fields in black hole geometries within a 4D spacetime., Comment: 11 pages, 3 figures

Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention employed in the original ViT. Regional attention restricts pixel interactions within specific regions, while sparse attention disperses them across sparse grids. These differing approaches pose a challenge between maintaining hierarchical relationships vs. capturing a global context. In this study, drawing inspiration from atrous convolution, we propose Atrous Attention, a blend of regional and sparse attention that dynamically integrates both local and global information while preserving hierarchical structures. Based on this, we introduce a versatile, hybrid vision transformer backbone called ACC-ViT, tailored for standard vision tasks. Our compact model achieves approximately 84% accuracy on ImageNet-1K with fewer than 28.5 million parameters, outperforming the state-of-the-art MaxViT by 0.42% while requiring 8.4% fewer parameters., Comment: Accepted as a Workshop Paper at T4V@CVPR2024. arXiv admin note: substantial text overlap with arXiv:2403.04200

Glavan and Lin [Phys. Rev. Lett. 124, 081301 (2020)] have recently proposed a consistent model of Einstein-Gauss-Bonnet modified gravity in four spacetime dimensions. This model predicts significant contributions of the Gauss-Bonnet coupling parameter $\alpha$ to gravitational dynamics, while circumventing the Lovelock theorem and avoiding Ostrogradsky instability. As a powerful competitor to general relativity, the model has been examined on various phenomenological grounds. Here, we employ a technique from thermodynamic geometry to analyze the thermodynamic phase structure of a charged black hole with a quantum gravity-inspired entropy relation in this novel modified gravity scenario. Based on the sign and magnitude of thermodynamic curvature, we demonstrate that while the theory does not significantly impact larger black holes, it may lead to multiple phase transitions and accelerate the formation of black hole remnants at short-distance scales compared to general relativity. Our analysis focuses solely on the non-extremal geometry case where $M>\sqrt{Q^2+\alpha}$, with $M$ and $Q$ representing the mass and charge of the black hole, respectively. We believe that these results may offer insights for testing the phenomenological consistency of the theory as a potential alternative to the standard Einstein paradigm., Comment: 15 pages, 9 figures

Interpretability and explainability are among the most important challenges of modern artificial intelligence, being mentioned even in various legislative sources. In this article, we develop a method for extracting immediately human interpretable classifiers from tabular data. The classifiers are given in the form of short Boolean formulas built with propositions that can either be directly extracted from categorical attributes or dynamically computed from numeric ones. Our method is implemented using Answer Set Programming. We investigate seven datasets and compare our results to ones obtainable by state-of-the-art classifiers for tabular data, namely, XGBoost and random forests. Over all datasets, the accuracies obtainable by our method are similar to the reference methods. The advantage of our classifiers in all cases is that they are very short and immediately human intelligible as opposed to the black-box nature of the reference methods.

Electrocardiogram (ECG) signals, profiling the electrical activities of the heart, are used for a plethora of diagnostic applications. However, ECG systems require multiple leads or channels of signals to capture the complete view of the cardiac system, which limits their application in smartwatches and wearables. In this work, we propose a modally reduced representation learning method for ECG signals that is capable of generating channel-agnostic, unified representations for ECG signals. Through joint optimization of reconstruction and alignment, we ensure that the embeddings of the different channels contain an amalgamation of the overall information across channels while also retaining their specific information. On an independent test dataset, we generated highly correlated channel embeddings from different ECG channels, leading to a moderate approximation of the 12-lead signals from a single-channel embedding. Our generated embeddings can work as competent features for ECG signals for downstream tasks., Comment: Accepted as a Workshop Paper at TS4H@ICLR2024

This work presents Unbundle-Rewrite-Rebundle (URR), a system for detecting privacy-harming portions of bundled JavaScript code and rewriting that code at runtime to remove the privacy-harming behavior without breaking the surrounding code or overall application. URR is a novel solution to the problem of JavaScript bundles, where websites pre-compile multiple code units into a single file, making it impossible for content filters and ad-blockers to differentiate between desired and unwanted resources. Where traditional content filtering tools rely on URLs, URR analyzes the code at the AST level, and replaces harmful AST sub-trees with privacy-and-functionality maintaining alternatives. We present an open-sourced implementation of URR as a Firefox extension and evaluate it against JavaScript bundles generated by the most popular bundling system (Webpack) deployed on the Tranco 10k. We evaluate URR by precision (1.00), recall (0.95), and speed (0.43s per script) when detecting and rewriting three representative privacy-harming libraries often included in JavaScript bundles, and find URR to be an effective approach to a large-and-growing blind spot unaddressed by current privacy tools., Comment: In Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS '24)

Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn invariant features with respect to a protected variable (e.g., race when classifying sex from face images) or enforce CI relative to the protected attribute only on the model output (e.g., the sex label). Neither of these methods are effective in enforcing CI in high-dimensional feature spaces. In this paper, we focus on a nascent approach characterizing the CI constraint in terms of two Jensen-Shannon divergence terms, and we extend it to high-dimensional feature spaces using a novel dynamic sampling strategy. In doing so, we introduce a new training paradigm that can be applied to any encoder architecture. We are able to enforce conditional independence of the diffusion autoencoder latent representation with respect to any protected attribute under the equalized odds constraint and show that this approach enables causal image generation with controllable latent spaces. Our experimental results demonstrate that our approach can achieve high accuracy on downstream tasks while upholding equality of odds., Comment: To appear at the 2024 IEEE CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision

We study in this paper optimal mass transport over a strongly connected, directed graph on a given discrete time interval. Differently from previous literature, we do not assume full knowledge of the initial and final goods distribution over the network nodes. In spite of the meager information, we show that it is possible to characterize the most likely flow in two important cases: The first one is when the initial and/or final distribution is only known on proper subsets of the nodes. The second case is when only some moments of the marginal distributions are known. As an important by-product, we determine the most likely initial and final marginals on the whole state space.

Model-based deep learning methods such as loop unrolling (LU) and deep equilibrium model}(DEQ) extensions offer outstanding performance in solving inverse problems (IP). These methods unroll the optimization iterations into a sequence of neural networks that in effect learn a regularization function from data. While these architectures are currently state-of-the-art in numerous applications, their success heavily relies on the accuracy of the forward model. This assumption can be limiting in many physical applications due to model simplifications or uncertainties in the apparatus. To address forward model mismatch, we introduce an untrained forward model residual block within the model-based architecture to match the data consistency in the measurement domain for each instance. We propose two variants in well-known model-based architectures (LU and DEQ) and prove convergence under mild conditions. Our approach offers a unified solution that is less parameter-sensitive, requires no additional data, and enables simultaneous fitting of the forward model and reconstruction in a single pass, benefiting both linear and nonlinear inverse problems. The experiments show significant quality improvement in removing artifacts and preserving details across three distinct applications, encompassing both linear and nonlinear inverse problems. Moreover, we highlight reconstruction effectiveness in intermediate steps and showcase robustness to random initialization of the residual block and a higher number of iterations during evaluation. Code is available at \texttt{https://github.com/InvProbs/A-adaptive-model-based-methods}., Comment: Published in Transactions in Machine Learning Research (TMLR)

We introduce and study flipped non-associative polynomial rings. In particular, we show that all Cayley-Dickson algebras naturally appear as quotients of a certain type of such rings; this extends the classical construction of the complex numbers (and quaternions) as a quotient of a (skew) polynomial ring to the octonions, and beyond. We also extend some classical results on algebraic properties of Cayley-Dickson algebras by McCrimmon to a class of flipped non-associative polynomial rings., Comment: 17 pages; corrected an error; fixed some typos

Transformers have elevated to the state-of-the-art vision architectures through innovations in attention mechanism inspired from visual perception. At present two classes of attentions prevail in vision transformers, regional and sparse attention. The former bounds the pixel interactions within a region; the latter spreads them across sparse grids. The opposing natures of them have resulted in a dilemma between either preserving hierarchical relation or attaining a global context. In this work, taking inspiration from atrous convolution, we introduce Atrous Attention, a fusion of regional and sparse attention, which can adaptively consolidate both local and global information, while maintaining hierarchical relations. As a further tribute to atrous convolution, we redesign the ubiquitous inverted residual convolution blocks with atrous convolution. Finally, we propose a generalized, hybrid vision transformer backbone, named ACC-ViT, following conventional practices for standard vision tasks. Our tiny version model achieves $\sim 84 \%$ accuracy on ImageNet-1K, with less than $28.5$ million parameters, which is $0.42\%$ improvement over state-of-the-art MaxViT while having $8.4\%$ less parameters. In addition, we have investigated the efficacy of ACC-ViT backbone under different evaluation settings, such as finetuning, linear probing, and zero-shot learning on tasks involving medical image analysis, object detection, and language-image contrastive learning. ACC-ViT is therefore a strong vision backbone, which is also competitive in mobile-scale versions, ideal for niche applications with small datasets.