Search

In today's world, marked by social distancing and lockdowns, the development of digital financial services is becoming increasingly important, but there is little empirical work documenting the most important factors that contribute to the process of financial and digital inclusion. Because the speed with which states adapt to digital financial services is critical, we must ask how prepared states are for this transition and how far they have progressed in terms of financial and digital inclusion. In this context, the goal of this article is, on the one hand, to propose a financial responsibility process framework capable of raising awareness of the most important harmonized key levels of financial and digital inclusion process that, when properly managed, can lead to achieving an optimal level of financial responsibility, and, on the other hand, to assess the financial and digital inclusion process of two different age groups of individuals who are active in the financial environment (15-34 and 35-59 age groups). The Analytical Hierarchy Process AHP and Fuzzy AHP approaches are proposed as a framework for assessing the mechanism of financial and digital inclusion in five East Central European countries. The findings reflect differences between the analyzed countries in terms of the key levels of financial and digital inclusion (where digital and financial education are the most important levels), with Croatia, Czech Republic, and Poland being the most integrated and Romania being the least. According to the findings, as a country or region's level of financial and digital inclusion increases, so does its level of financial responsibility. This research can be a useful tool in raising awareness about the importance of directed behavior for financial responsibility, particularly for policymakers.

In this article, models for assessing national intangible resources are analysed through a lecture in the literature, and the best-known evaluation methods are categorized into academic models and models of international organizations, with the most important differences being identified. The European Innovation Scoreboard (EIS) and the World Economic Forum annual reports on Global Competitiveness were considered to assess Romania's position in the international context in terms of intangible assets. Despite the importance of intangible resources at national level and the fact that they are an important factor in determining economic growth in the current knowledge-based economy, this article concludes that Romania's position in the international context regarding intangible assets is very weak, with many weak points in research and innovation performance compared to other EU Member States. Therefore, there is a need in our country to re-evaluate the areas where all efforts need to be focused to stimulate innovation performance, to properly manage national intangible resources, a crucial process for improving the quality of life.

This paper addresses the issue of intellectual property management in the knowledge-based economy. The starting point in carrying out the study is the presentation of some concepts regarding in the first phase, the intellectual capital. Arguments are made that the knowledge-based economy is a challenge for the current century. The subject of intellectual property is approached through the prism of a topical concept operationalized in the current global economic context. The main institutions that are directly related to this concept are mentioned. The topic of patents related to WOS indexed scientific papers is also debated, along with a series of statistics and studies on the state of patent protection worldwide in the top fields. The last part of the paper contains the conclusions and own points of view on the debated topic.

Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline to remove ambiguous samples. We then design a number of network architecture components to enhance scalability, including a side-tuning feature backbone that adapts rich monocular priors from vision foundation models to mitigate the sim-to-real gap, and long-range context reasoning for effective cost volume filtering. Together, these components lead to strong robustness and accuracy across domains, establishing a new standard in zero-shot stereo depth estimation. Project page: https://nvlabs.github.io/FoundationStereo/

One of the themes that have been approached more and more within the specialised literature is being represented by economic cycles. The analysis of these is very useful in the long term predictions, in finding solutions for the economic raise and for detecting the economic crisis. At the same time, it is underlined in a lot of scientific and research papers, the importance of the sustainable development in the present and future society. In this paper we intend to bring contributions to the study of the cycles of a sustainable economy and we will analyse it having in mind the purpose of creating the sustainable economy. We will demonstrate the fact that curves that represent graphically all these, are not simple logistics anymore, bi-logistics or multilogistics curves, but curves in plan that are obtained by composing logistics functions with the function of the sustainable development or with the function that shapes the economic component of it mathematically. We will present an interpretation of mathematic models within the frame of the sustainable development.

Inclusiveness and economic development have been slowed by the pandemics and military conflicts. This study investigates the main determinants of inclusiveness at the European level. A multi-method approach is used, with Principal Component Analysis (PCA) applied to create the Inclusiveness Index and Generalised Method of Moments (GMM) analysis used to investigate the determinants of inclusiveness. The data comprises a range of 22 years, from 2000 to 2021, for 32 European countries. The determinants of inclusiveness and their effects were identified. First, economic growth, industrial upgrading, electricity consumption, digitalisation, and the quantitative aspect of governance, all have a positive impact on inclusive growth in Europe. Second, the level of CO2 emissions and inflation have a negative impact on inclusiveness. Tomorrow's inclusive and sustainable growth must include investments in renewable energy, digital infrastructure, inequality policies, sustainable governance, human capital, and inflation management. These findings can help decision makers design inclusive growth policies.

The goal of this study is to propose a new concept, Sustainable Economic Value, to define it logically, and to build a simplified model for its evaluation.

This article presents a comprehensive methodology for processing financial datasets of Apple Inc., encompassing quarterly income and daily stock prices, spanning from March 31, 2009, to December 31, 2023. Leveraging 60 observations for quarterly income and 3774 observations for daily stock prices, sourced from Macrotrends and Yahoo Finance respectively, the study outlines five distinct datasets crafted through varied preprocessing techniques. Through detailed explanations of aggregation, interpolation (linear, polynomial, and cubic spline) and lagged variables methods, the study elucidates the steps taken to transform raw data into analytically rich datasets. Subsequently, the article delves into regression analysis, aiming to decipher which of the five data processing methods best suits capital market analysis, by employing both linear and polynomial regression models on each preprocessed dataset and evaluating their performance using a range of metrics, including cross-validation score, MSE, MAE, RMSE, R-squared, and Adjusted R-squared. The research findings reveal that linear interpolation with polynomial regression emerges as the top-performing method, boasting the lowest validation MSE and MAE values, alongside the highest R-squared and Adjusted R-squared values.

The monetary transmission channel is disrupted by many factors, especially securitization and liquidity traps. In our study we try to estimate the effect of securitization on the interest elasticity and to identify if a liquidity trap occurred during 1954Q3-2019Q3. The yield curve inversion mechanism shows us that economic cycles are very sensitive to decreasing profitability of banks. However there is no evidence that restoring their profits will ensure a strong recovery. In this regard, we research the low effect of Quantitative Easing (QE) upon economic growth and analyze whether securitization and liquidity traps posed challenges to QE or is it the mainstream theory flawed. In this regard we will examine the main weaknesses of QE, respectively the speculative behavior induced by artificial low rates and its unequal distribution. We propose a new form of QE that will relief households and not reward banks for their risky behavior before recession.

Phylogenetic trees elucidate evolutionary relationships among species, but phylogenetic inference remains challenging due to the complexity of combining continuous (branch lengths) and discrete parameters (tree topology). Traditional Markov Chain Monte Carlo methods face slow convergence and computational burdens. Existing Variational Inference methods, which require pre-generated topologies and typically treat tree structures and branch lengths independently, may overlook critical sequence features, limiting their accuracy and flexibility. We propose PhyloGen, a novel method leveraging a pre-trained genomic language model to generate and optimize phylogenetic trees without dependence on evolutionary models or aligned sequence constraints. PhyloGen views phylogenetic inference as a conditionally constrained tree structure generation problem, jointly optimizing tree topology and branch lengths through three core modules: (i) Feature Extraction, (ii) PhyloTree Construction, and (iii) PhyloTree Structure Modeling. Meanwhile, we introduce a Scoring Function to guide the model towards a more stable gradient descent. We demonstrate the effectiveness and robustness of PhyloGen on eight real-world benchmark datasets. Visualization results confirm PhyloGen provides deeper insights into phylogenetic relationships.

The $M1$ transition strengths between excited $2^+$ states of the neutron-rich, radioactive nuclide $^{132}$Te have been studied through direct lifetime measurements using the Doppler-shift attenuation method in a two-neutron transfer reaction on a $^{130}$Te target. An unambiguous identification of the lowest-lying mixed-symmetry $2^+$ state has been achieved on the basis of the large $B(M1;2^+_2\rightarrow2^+_1$)=0.18(2) $\mu_\mathrm{N}^2$ transition strength, in agreement with shell-model calculations. Results are compared to the shell model, and the analysis of both, data and calculations, unambiguously identifies the second-excited $2^+$ state of $^{132}$Te as the one-quadrupole phonon mixed-symmetry state of this isotope. A lowering of the energy and $B(M1;2^+_\mathrm{ms}\rightarrow 2^+_1)$ strength within the $N$=80 isotones toward the $Z$=50 shell closure is observed, which goes alongside with the lowering of the $E2$ collectivity approaching the magic proton shell.

Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as linguistic content when both modalities are necessary to formulate an accurate answer. We hypothesize that hallucinations arise due to the lack of effective visual grounding in current LVLMs. This issue extends to vision-language benchmarks, where it is difficult to make the image indispensable for accurate answer generation, particularly in vision question-answering tasks. In this work, we introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding and to evaluate their effectiveness in achieving it. These datasets can be utilized for both training and assessing an LVLM's ability to use image content as substantive evidence rather than relying solely on linguistic priors, providing insights into the model's reliance on visual information. To demonstrate the utility of our dataset, we introduce an innovative training task that outperforms baselines alongside a validation method and application for explainability. The code is available at https://github.com/IntelLabs/fivl.

Antibodies are Y-shaped proteins that protect the host by binding to specific antigens, and their binding is mainly determined by the Complementary Determining Regions (CDRs) in the antibody. Despite the great progress made in CDR design, existing computational methods still encounter several challenges: 1) poor capability of modeling complex CDRs with long sequences due to insufficient contextual information; 2) conditioned on pre-given antigenic epitopes and their static interaction with the target antibody; 3) neglect of specificity during antibody optimization leads to non-specific antibodies. In this paper, we take into account a variety of node features, edge features, and edge relations to include more contextual and geometric information. We propose a novel Relation-Aware Antibody Design (RAAD) framework, which dynamically models antigen-antibody interactions for co-designing the sequences and structures of antigen-specific CDRs. Furthermore, we propose a new evaluation metric to better measure antibody specificity and develop a contrasting specificity-enhancing constraint to optimize the specificity of antibodies. Extensive experiments have demonstrated the superior capability of RAAD in terms of antibody modeling, generation, and optimization across different CDR types, sequence lengths, pre-training strategies, and input contexts.

In this paper, we determine an exact solution to the governing equations in spherical coordinates for an inviscid, incompressible fluid. This solution describes a steady, purely azimuthal equatorial flow with an associated free surface. Using functional analytic techniques, we demonstrate that if a free surface is known beforehand, the variations in pressure needed to achieve this surface implicitly define the shape of the free surface in a unique way.

While Large Vision Language Models (LVLMs) have become masterly capable in reasoning over human prompts and visual inputs, they are still prone to producing responses that contain misinformation. Identifying incorrect responses that are not grounded in evidence has become a crucial task in building trustworthy AI. Explainability methods such as gradient-based relevancy maps on LVLM outputs can provide an insight on the decision process of models, however these methods are often computationally expensive and not suited for on-the-fly validation of outputs. In this work, we propose FastRM, an effective way for predicting the explainable Relevancy Maps of LVLM models. Experimental results show that employing FastRM leads to a 99.8% reduction in compute time for relevancy map generation and an 44.4% reduction in memory footprint for the evaluated LVLM, making explainable AI more efficient and practical, thereby facilitating its deployment in real-world applications.

We survey Kondrat'ev--Landis' conjecture, providing an up-to-date account of the main advances and describing the techniques developed. We complement the overview with references and formulations of the problem in further closely connected contexts., Comment: 25 pages

Identifying T-cell receptors (TCRs) that interact with antigenic peptides provides the technical basis for developing vaccines and immunotherapies. The emergent deep learning methods excel at learning antigen binding patterns from known TCRs but struggle with novel or sparsely represented antigens. However, binding specificity for unseen antigens or exogenous peptides is critical. We introduce a domain-adaptive peptide-agnostic learning framework DapPep for universal TCR-antigen binding affinity prediction to address this challenge. The lightweight self-attention architecture combines a pre-trained protein language model with an inner-loop self-supervised regime to enable robust TCR-peptide representations. Extensive experiments on various benchmarks demonstrate that DapPep consistently outperforms existing tools, showcasing robust generalization capability, especially for data-scarce settings and unseen peptides. Moreover, DapPep proves effective in challenging clinical tasks such as sorting reactive T cells in tumor neoantigen therapy and identifying key positions in 3D structures.

Computational protein design (CPD) offers transformative potential for bioengineering, but current deep CPD models, focused on universal domains, struggle with function-specific designs. This work introduces a novel CPD paradigm tailored for functional design tasks, particularly for enzymes-a key protein class often lacking specific application efficiency. To address structural data scarcity, we present CrossDesign, a domain-adaptive framework that leverages pretrained protein language models (PPLMs). By aligning protein structures with sequences, CrossDesign transfers pretrained knowledge to structure models, overcoming the limitations of limited structural data. The framework combines autoregressive (AR) and non-autoregressive (NAR) states in its encoder-decoder architecture, applying it to enzyme datasets and pan-proteins. Experimental results highlight CrossDesign's superior performance and robustness, especially with out-of-domain enzymes. Additionally, the model excels in fitness prediction when tested on large-scale mutation data, showcasing its stability.

David Marr's seminal theory of vision proposes that the human visual system operates through a sequence of three stages, known as the 2D sketch, the 2.5D sketch, and the 3D model. In recent years, Deep Neural Networks (DNN) have been widely thought to have reached a level comparable to human vision. However, the mechanisms by which DNNs accomplish this and whether they adhere to Marr's 2D--2.5D--3D construction theory remain unexplored. In this paper, we delve into the perception task to explore these questions and find evidence supporting Marr's theory. We introduce a graphics probe, a sub-network crafted to reconstruct the original image from the network's intermediate layers. The key to the graphics probe is its flexible architecture that supports image in both 2D and 3D formats, as well as in a transitional state between them. By injecting graphics probes into neural networks, and analyzing their behavior in reconstructing images, we find that DNNs initially encode images as 2D representations in low-level layers, and finally construct 3D representations in high-level layers. Intriguingly, in mid-level layers, DNNs exhibit a hybrid state, building a geometric representation that s sur normals within a narrow depth range, akin to the appearance of a low-relief sculpture. This stage resembles the 2.5D representations, providing a view of how DNNs evolve from 2D to 3D in the perception process. The graphics probe therefore serves as a tool for peering into the mechanisms of DNN, providing empirical support for Marr's theory.

Spatial understanding is a crucial capability for robots to make grounded decisions based on their environment. This foundational skill enables robots not only to perceive their surroundings but also to reason about and interact meaningfully within the world. In modern robotics, these capabilities are taken on by visual language models, and they face significant challenges when applied to spatial reasoning context due to their training data sources. These sources utilize general-purpose image datasets, and they often lack sophisticated spatial scene understanding capabilities. For example, the datasets do not address reference frame comprehension - spatial relationships require clear contextual understanding, whether from an ego-centric, object-centric, or world-centric perspective, which allow for effective real-world interaction. To address this issue, we introduce RoboSpatial, a large-scale spatial understanding dataset consisting of real indoor and tabletop scenes captured as 3D scans and egocentric images, annotated with rich spatial information relevant to robotics. The dataset includes 1M images, 5K 3D scans, and 3M annotated spatial relationships, with paired 2D egocentric images and 3D scans to make it both 2D and 3D ready. Our experiments show that models trained with RoboSpatial outperform baselines on downstream tasks such as spatial affordance prediction, spatial relationship prediction, and robotics manipulation.

Modern day Language Models see extensive use in text classification, yet this comes at significant computational cost. Compute-effective classification models are needed for low-resource environments, most notably on edge devices. We introduce Adaptable Embeddings Networks (AEN), a novel dual-encoder architecture using Kernel Density Estimation (KDE). This architecture allows for runtime adaptation of classification criteria without retraining and is non-autoregressive. Through thorough synthetic data experimentation, we demonstrate our model outputs comparable and in certain cases superior results to that of autoregressive models an order of magnitude larger than AEN's size. The architecture's ability to preprocess and cache condition embeddings makes it ideal for edge computing applications and real-time monitoring systems., Comment: 20 pages

The standardization of an interface for dense linear algebra operations in the BLAS standard has enabled interoperability between different linear algebra libraries, thereby boosting the success of scientific computing, in particular in scientific HPC. Despite numerous efforts in the past, the community has not yet agreed on a standardization for sparse linear algebra operations due to numerous reasons. One is the fact that sparse linear algebra objects allow for many different storage formats, and different hardware may favor different storage formats. This makes the definition of a FORTRAN-style all-circumventing interface extremely challenging. Another reason is that opposed to dense linear algebra functionality, in sparse linear algebra, the size of the sparse data structure for the operation result is not always known prior to the information. Furthermore, as opposed to the standardization effort for dense linear algebra, we are late in the technology readiness cycle, and many production-ready software libraries using sparse linear algebra routines have implemented and committed to their own sparse BLAS interface. At the same time, there exists a demand for standardization that would improve interoperability, and sustainability, and allow for easier integration of building blocks. In an inclusive, cross-institutional effort involving numerous academic institutions, US National Labs, and industry, we spent two years designing a hardware-portable interface for basic sparse linear algebra functionality that serves the user needs and is compatible with the different interfaces currently used by different vendors. In this paper, we present a C++ API for sparse linear algebra functionality, discuss the design choices, and detail how software developers preserve a lot of freedom in terms of how to implement functionality behind this API., Comment: 43 pages

The evolution of molecular dynamics (MD) simulations has been intimately linked to that of computing hardware. For decades following the creation of MD, simulations have improved with computing power along the three principal dimensions of accuracy, atom count (spatial scale), and duration (temporal scale). Since the mid-2000s, computer platforms have however failed to provide strong scaling for MD as scale-out CPU and GPU platforms that provide substantial increases to spatial scale do not lead to proportional increases in temporal scale. Important scientific problems therefore remained inaccessible to direct simulation, prompting the development of increasingly sophisticated algorithms that present significant complexity, accuracy, and efficiency challenges. While bespoke MD-only hardware solutions have provided a path to longer timescales for specific physical systems, their impact on the broader community has been mitigated by their limited adaptability to new methods and potentials. In this work, we show that a novel computing architecture, the Cerebras Wafer Scale Engine, completely alters the scaling path by delivering unprecedentedly high simulation rates up to 1.144M steps/second for 200,000 atoms whose interactions are described by an Embedded Atom Method potential. This enables direct simulations of the evolution of materials using general-purpose programmable hardware over millisecond timescales, dramatically increasing the space of direct MD simulations that can be carried out.

Time series generation has emerged as an essential tool for analyzing temporal data across numerous fields. While diffusion models have recently gained significant attention in generating high-quality time series, they tend to be computationally demanding and reliant on complex stochastic processes. To address these limitations, we introduce FM-TS, a rectified Flow Matching-based framework for Time Series generation, which simplifies the time series generation process by directly optimizing continuous trajectories. This approach avoids the need for iterative sampling or complex noise schedules typically required in diffusion-based models. FM-TS is more efficient in terms of training and inference. Moreover, FM-TS is highly adaptive, supporting both conditional and unconditional time series generation. Notably, through our novel inference design, the model trained in an unconditional setting can seamlessly generalize to conditional tasks without the need for retraining. Extensive benchmarking across both settings demonstrates that FM-TS consistently delivers superior performance compared to existing approaches while being more efficient in terms of training and inference. For instance, in terms of discriminative score, FM-TS achieves 0.005, 0.019, 0.011, 0.005, 0.053, and 0.106 on the Sines, Stocks, ETTh, MuJoCo, Energy, and fMRI unconditional time series datasets, respectively, significantly outperforming the second-best method which achieves 0.006, 0.067, 0.061, 0.008, 0.122, and 0.167 on the same datasets. We have achieved superior performance in solar forecasting and MuJoCo imputation tasks, significantly enhanced by our innovative $t$ power sampling method. The code is available at https://github.com/UNITES-Lab/FMTS.

We present supernova (SN) 2023ufx, a unique Type IIP SN with the shortest known plateau duration ($t_\mathrm{PT}$ $\sim$47 days), a luminous V-band peak ($M_{V}$ = $-$18.42 $\pm$ 0.08 mag), and a rapid early decline rate ($s1$ = 3.47 $\pm$ 0.09 mag (50 days)$^{-1}$). By comparing observed photometry to a hydrodynamic MESA+STELLA model grid, we constrain the progenitor to be a massive red supergiant with M$_\mathrm{ZAMS}$ $\simeq$19 - 25 M$_{\odot}$. Independent comparisons with nebular spectral models also suggest an initial He-core mass of $\sim$6 M$_{\odot}$, and thus a massive progenitor. For a Type IIP, SN 2023ufx produced an unusually high amount of nickel ($^{56}$Ni) $\sim$0.14 $\pm$ 0.02 M$_{\odot}$, during the explosion. We find that the short plateau duration in SN 2023ufx can be explained with the presence of a small hydrogen envelope (M$_\mathrm{H_\mathrm{env}}$ $\simeq$1.2 M$_{\odot}$), suggesting partial stripping of the progenitor. About $\simeq$0.09 M$_{\odot}$ of CSM through mass loss from late-time stellar evolution of the progenitor is needed to fit the early time ($\lesssim$10 days) pseudo-bolometric light curve. Nebular line diagnostics of broad and multi-peak components of [O I] $\lambda\lambda$6300, 6364, H$\alpha$, and [Ca II] $\lambda \lambda$7291, 7323 suggest that the explosion of SN 2023ufx could be inherently asymmetric, preferentially ejecting material along our line-of-sight., Comment: Submitted to ApJ, 30 pages, 19 figures

Post-translational modifications (PTMs) profoundly expand the complexity and functionality of the proteome, regulating protein attributes and interactions that are crucial for biological processes. Accurately predicting PTM sites and their specific types is therefore essential for elucidating protein function and understanding disease mechanisms. Existing computational approaches predominantly focus on protein sequences to predict PTM sites, driven by the recognition of sequence-dependent motifs. However, these approaches often overlook protein structural contexts. In this work, we first compile a large-scale sequence-structure PTM dataset, which serves as the foundation for fair comparison. We introduce the MeToken model, which tokenizes the micro-environment of each amino acid, integrating both sequence and structural information into unified discrete tokens. This model not only captures the typical sequence motifs associated with PTMs but also leverages the spatial arrangements dictated by protein tertiary structures, thus providing a holistic view of the factors influencing PTM sites. Designed to address the long-tail distribution of PTM types, MeToken employs uniform sub-codebooks that ensure even the rarest PTMs are adequately represented and distinguished. We validate the effectiveness and generalizability of MeToken across multiple datasets, demonstrating its superior performance in accurately identifying PTM types. The results underscore the importance of incorporating structural data and highlight MeToken's potential in facilitating accurate and comprehensive PTM predictions, which could significantly impact proteomics research. The code and datasets are available at https://github.com/A4Bio/MeToken., Comment: 26 pages, 20 figures, 10 tables

We introduce SPOT, an object-centric imitation learning framework. The key idea is to capture each task by an object-centric representation, specifically the SE(3) object pose trajectory relative to the target. This approach decouples embodiment actions from sensory inputs, facilitating learning from various demonstration types, including both action-based and action-less human hand demonstrations, as well as cross-embodiment generalization. Additionally, object pose trajectories inherently capture planning constraints from demonstrations without the need for manually crafted rules. To guide the robot in executing the task, the object trajectory is used to condition a diffusion policy. We show improvement compared to prior work on RLBench simulated tasks. In real-world evaluation, using only eight demonstrations shot on an iPhone, our approach completed all tasks while fully complying with task constraints. Project page: https://nvlabs.github.io/object_centric_diffusion

Abstract Recent advances in immunology and synthetic biology have accelerated the development of deep generative methods for DNA sequence design. Two dominant approaches in this field are AutoRegressive (AR) models and Diffusion Models (DMs). However, genomic sequences are functionally heterogeneous, consisting of multiple connected regions (e.g., Promoter Regions, Exons, and Introns) where elements within each region come from the same probability distribution, but the overall sequence is non-homogeneous. This heterogeneous nature presents challenges for a single model to accurately generate genomic sequences. In this paper, we analyze the properties of AR models and DMs in heterogeneous genomic sequence generation, pointing out crucial limitations in both methods: (i) AR models capture the underlying distribution of data by factorizing and learning the transition probability but fail to capture the global property of DNA sequences. (ii) DMs learn to recover the global distribution but tend to produce errors at the base pair level. To overcome the limitations of both approaches, we propose a post-training sampling method, termed Absorb & Escape (A&E) to perform compositional generation from AR models and DMs. This approach starts with samples generated by DMs and refines the sample quality using an AR model through the alternation of the Absorb and Escape steps. To assess the quality of generated sequences, we conduct extensive experiments on 15 species for conditional and unconditional DNA generation. The experiment results from motif distribution, diversity checks, and genome integration tests unequivocally show that A&E outperforms state-of-the-art AR models and DMs in genomic sequence generation., Comment: Accepted at NeurIPS 2024

Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization, by simplifying complex datasets while retaining essential information. However, the challenge of balancing DR accuracy and interpretability remains crucial, particularly for users dealing with high-dimensional data. Traditional DR methods often face a trade-off between precision and transparency, where optimizing for performance can lead to reduced interpretability, and vice versa. This limitation is especially prominent in real-world applications such as image, tabular, and text data analysis, where both accuracy and interpretability are critical. To address these challenges, this work introduces the MOE-based Hyperbolic Interpretable Deep Manifold Transformation (DMT-HI). The proposed approach combines hyperbolic embeddings, which effectively capture complex hierarchical structures, with Mixture of Experts (MOE) models, which dynamically allocate tasks based on input features. DMT-HI enhances DR accuracy by leveraging hyperbolic embeddings to represent the hierarchical nature of data, while also improving interpretability by explicitly linking input data, embedding outcomes, and key features through the MOE structure. Extensive experiments demonstrate that DMT-HI consistently achieves superior performance in both DR accuracy and model interpretability, making it a robust solution for complex data analysis. The code is available at \url{https://github.com/zangzelin/code_dmthi}., Comment: 14 pages, 8 figures

We introduce GRS (Generating Robotic Simulation tasks), a novel system to address the challenge of real-to-sim in robotics, computer vision, and AR/VR. GRS enables the creation of digital twin simulations from single real-world RGB-D observations, complete with diverse, solvable tasks for virtual agent training. We use state-of-the-art vision-language models (VLMs) to achieve a comprehensive real-to-sim pipeline. GRS operates in three stages: 1) scene comprehension using SAM2 for object segmentation and VLMs for object description, 2) matching identified objects with simulation-ready assets, and 3) generating contextually appropriate robotic tasks. Our approach ensures simulations align with task specifications by generating test suites designed to verify adherence to the task specification. We introduce a router that iteratively refines the simulation and test code to ensure the simulation is solvable by a robot policy while remaining aligned to the task specification. Our experiments demonstrate the system's efficacy in accurately identifying object correspondence, which allows us to generate task environments that closely match input environments, and enhance automated simulation task generation through our novel router mechanism.

Molecular relational learning (MRL) is crucial for understanding the interaction behaviors between molecular pairs, a critical aspect of drug discovery and development. However, the large feasible model space of MRL poses significant challenges to benchmarking, and existing MRL frameworks face limitations in flexibility and scope. To address these challenges, avoid repetitive coding efforts, and ensure fair comparison of models, we introduce FlexMol, a comprehensive toolkit designed to facilitate the construction and evaluation of diverse model architectures across various datasets and performance metrics. FlexMol offers a robust suite of preset model components, including 16 drug encoders, 13 protein sequence encoders, 9 protein structure encoders, and 7 interaction layers. With its easy-to-use API and flexibility, FlexMol supports the dynamic construction of over 70, 000 distinct combinations of model architectures. Additionally, we provide detailed benchmark results and code examples to demonstrate FlexMol's effectiveness in simplifying and standardizing MRL model development and comparison.

This paper focuses on adapting the functionalities of the FastPitch model to the Romanian language; extending the set of speakers from one to eighteen; synthesising speech using an anonymous identity; and replicating the identities of new, unseen speakers. During this work, the effects of various configurations and training strategies were tested and discussed, along with their advantages and weaknesses. Finally, we settled on a new configuration, built on top of the FastPitch architecture, capable of producing natural speech synthesis, for both known (identities from the training dataset) and unknown (identities learnt through short reference samples) speakers. The anonymous speaker can be used for text-to-speech synthesis, if one wants to cancel out the identity information while keeping the semantic content whole and clear. At last, we discussed possible limitations of our work, which will form the basis for future investigations and advancements., Comment: Accepted at 2024 IEEE 20th International Conference on Intelligent Computer Communication and Processing (ICCP 2024)

Here we report on the first measurements of the $\gamma$-ray strength functions and nuclear level densities of ${}^{112,114}$Sn performed at the 9~MV Tandem accelerator facilities at IFIN-HH using the Oslo method. We extract thermodynamic properties as well as both gross and fine properties of the pygmy dipole resonance for systematic comparison in the chain of Sn isotopes. The results are compared with microscopic models implemented in the TALYS reaction code, and the fully microscopic quasiparticle-phonon model for the underlying nuclear structure of the dipole strength in ${}^{112,114}$Sn. The experimental data and theoretical results are further included into the cross-section and reaction rate calculations for the $(\mathrm{n},\gamma)$ production reaction of the $p$-process nuclei ${}^{112,114}$Sn showing a significant increase in reaction rates at high temperatures compared to existing nuclear databases., Comment: 21 pages, 17 figures

This paper delves into the interplay between vision backbones and optimizers, unvealing an inter-dependent phenomenon termed \textit{\textbf{b}ackbone-\textbf{o}ptimizer \textbf{c}oupling \textbf{b}ias} (BOCB). We observe that canonical CNNs, such as VGG and ResNet, exhibit a marked co-dependency with SGD families, while recent architectures like ViTs and ConvNeXt share a tight coupling with the adaptive learning rate ones. We further show that BOCB can be introduced by both optimizers and certain backbone designs and may significantly impact the pre-training and downstream fine-tuning of vision models. Through in-depth empirical analysis, we summarize takeaways on recommended optimizers and insights into robust vision backbone architectures. We hope this work can inspire the community to question long-held assumptions on backbones and optimizers, stimulate further explorations, and thereby contribute to more robust vision systems. The source code and models are publicly available at https://bocb-ai.github.io/., Comment: Preprint V1. Online project at https://bocb-ai.github.io/

Biological tree analysis serves as a pivotal tool in uncovering the evolutionary and differentiation relationships among organisms, genes, and cells. Its applications span diverse fields including phylogenetics, developmental biology, ecology, and medicine. Traditional tree inference methods, while foundational in early studies, face increasing limitations in processing the large-scale, complex datasets generated by modern high-throughput technologies. Recent advances in deep learning offer promising solutions, providing enhanced data processing and pattern recognition capabilities. However, challenges remain, particularly in accurately representing the inherently discrete and non-Euclidean nature of biological trees. In this review, we first outline the key biological priors fundamental to phylogenetic and differentiation tree analyses, facilitating a deeper interdisciplinary understanding between deep learning researchers and biologists. We then systematically examine the commonly used data formats and databases, serving as a comprehensive resource for model testing and development. We provide a critical analysis of traditional tree generation methods, exploring their underlying biological assumptions, technical characteristics, and limitations. Current developments in deep learning-based tree generation are reviewed, highlighting both recent advancements and existing challenges. Furthermore, we discuss the diverse applications of biological trees across various biological domains. Finally, we propose potential future directions and trends in leveraging deep learning for biological tree research, aiming to guide further exploration and innovation in this field., Comment: 83 pages, 15 figures

We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity grounded in singular learning theory, to study the development of internal structure in transformer language models during training. By applying these \textit{refined LLCs} (rLLCs) to individual components of a two-layer attention-only transformer, we gain novel insights into the progressive differentiation and specialization of attention heads. Our methodology reveals how attention heads differentiate into distinct functional roles over the course of training, analyzes the types of data these heads specialize to process, and discovers a previously unidentified multigram circuit. These findings demonstrate that rLLCs provide a principled, quantitative toolkit for \textit{developmental interpretability}, which aims to understand models through their evolution across the learning process. More broadly, this work takes a step towards establishing the correspondence between data distributional structure, geometric properties of the loss landscape, learning dynamics, and emergent computational structures in neural networks.

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By leveraging a world model during training, the driving policy effectively mitigates covariate shift without requiring an excessive amount of training data. During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations, so that at runtime it can recover from perturbations outside the training distribution. Additionally, we introduce a novel transformer-based perception encoder that employs multi-view cross-attention and a learned scene query. We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing in the CARLA simulator, as well as showing the ability to handle perturbations in both CARLA and NVIDIA's DRIVE Sim., Comment: 7 pages, 6 figures, for ICRA 2025 conference, for associated video file, see https://youtu.be/fO7RZ57gVxk

Considering regions in a map to be adjacent when they have nonempty intersection (as opposed to the traditional view requiring intersection in a linear segment) leads to the concept of a facially complete graph: a plane graph that becomes complete when edges are added between every two vertices that lie on a face. Here we present a complete catalog of facially complete graphs: they fall into seven types. A consequence is that if q is the size of the largest face in a plane graph G that is facially complete, then G has at most Floor[3/2 q] vertices. This bound was known, but our proof is completely different from the 1998 approach of Chen, Grigni, and Papadimitriou. Our method also yields a count of the 2-connected facially complete graphs with n vertices. We also show that if a plane graph has at most two faces of size 4 and no larger face, then the addition of both diagonals to each 4-face leads to a graph that is 5-colorable.

This paper presents a novel deep neural network-based architecture tailored for Speech Emotion Recognition (SER). The architecture capitalises on dense interconnections among multiple layers of bidirectional dilated convolutions. A linear kernel dynamically fuses the outputs of these layers to yield the final emotion class prediction. This innovative architecture is denoted as TBDM-Net: Temporally-Aware Bi-directional Dense Multi-Scale Network. We conduct a comprehensive performance evaluation of TBDM-Net, including an ablation study, across six widely-acknowledged SER datasets for unimodal speech emotion recognition. Additionally, we explore the influence of gender-informed emotion prediction by appending either golden or predicted gender labels to the architecture's inputs or predictions. The implementation of TBDM-Net is accessible at: https://github.com/adrianastan/tbdm-net, Comment: In Proceedings of 2024 IEEE International Workshop on Machine Learning for Signal Processing, London, UK

In this paper we examine a mutual control problem for systems of two abstract evolution equations subject to a proportionality final condition. Related observability and semi-observability problems are discussed. The analysis employs a vector fixed-point approach, using matrices rather than constants, and applies the technique of Bielecki equivalent norms., Comment: arXiv admin note: text overlap with arXiv:2407.21131

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). However, most existing GNNs are based on message passing to perform feature aggregation and transformation, where the structural information is explicitly involved in the forward propagation by coupling with node features through graph convolution at each layer. As a result, subtle feature noise or structure perturbation may cause severe error propagation, resulting in extremely poor robustness. In this paper, we rethink the roles played by graph structural information in graph data training and identify that message passing is not the only path to modeling structural information. Inspired by this, we propose a simple but effective Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge to guide the computation of supervision signals, substituting the explicit message propagation as in GNNs. Specifically, it first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations. Finally, structural sparsification and self-contrasting are formulated as a bi-level optimization problem and solved in a unified framework. Extensive experiments have qualitatively and quantitatively demonstrated that the GSSC framework can produce truly encouraging performance with better generalization and robustness than other leading competitors.

As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at \url{https://github.com/Westlake-AI/Awesome-Mixup}., Comment: Preprint V1 with 27 pages main text. Online project at https://github.com/Westlake-AI/Awesome-Mixup

Objective: The Daily Phonotrauma Index (DPI) can quantify pathophysiological mechanisms associated with daily voice use in individuals with phonotraumatic vocal hyperfunction (PVH). Since DPI was developed based on week-long ambulatory voice monitoring, this study investigated if DPI can achieve comparable performance using (1) short laboratory speech tasks and (2) fewer than seven days of ambulatory data. Method: An ambulatory voice monitoring system recorded the vocal function/behavior of 134 females with PVH and vocally healthy matched controls in two different conditions. In the lab, the participants read the first paragraph of the Rainbow Passage and produced spontaneous speech (in-lab data). They were then monitored for seven days (in-field data). Separate DPI models were trained from in-lab and in-field data using the standard deviation of the difference between the magnitude of the first two harmonics (H1-H2) and the skewness of neck-surface acceleration magnitude. First, 10-fold cross-validation evaluated classification performance of in-lab and in-field DPIs. Second, the effect of the number of ambulatory monitoring days on the accuracy of in-field DPI classification was quantified. Results: The average in-lab DPI accuracy computed from the Rainbow passage and spontaneous speech were, respectively, 57.9% and 48.9%, which are close to chance performance. The average classification accuracy of in-field DPI was significantly higher with a very large effect size (73.4%, Cohens D = 1.8). Second, the average in-field DPI accuracy increased from 66.5% for one day to 75.0% for seven days, with the gain of including an additional day on accuracy dropping below 1 percentage point after 4 days., Comment: The paper is submitted to JSLHR

The cores of stars are the cosmic furnaces where light elements are fused into heavier nuclei. The fusion of hydrogen to helium initially powers all stars. The ashes of the fusion reactions are then predicted to serve as fuel in a series of stages, eventually transforming massive stars into a structure of concentric shells. These are composed of natal hydrogen on the outside, and consecutively heavier compositions inside, predicted to be dominated by helium, carbon/oxygen, oxygen/neon/magnesium, and oxygen/silicon/sulphur. Silicon and sulphur are fused into inert iron, leading to the collapse of the core and either a supernova explosion or the direct formation of a black hole. Stripped stars, where the outer hydrogen layer has been removed and the internal He-rich layer (in Wolf-Rayet WN stars) or even the C/O layer below it (in Wolf-Rayet WC/WO stars) are exposed, provide evidence for this shell structure, and the cosmic element production mechanism it reflects. The types of supernova explosions that arise from stripped stars embedded in shells of circumstellar material (most notably Type Ibn supernovae from stars with outer He layers, and Type Icn supernovae from stars with outer C/O layers) confirm this scenario. However, direct evidence for the most interior shells, which are responsible for the production of elements heavier than oxygen, is lacking. Here, we report the discovery of the first-of-its-kind supernova arising from a star peculiarly stripped all the way to the silicon and sulphur-rich internal layer. Whereas the concentric shell structure of massive stars is not under debate, it is the first time that such a thick, massive silicon and sulphur-rich shell, expelled by the progenitor shortly before the SN explosion, has been directly revealed., Comment: 48 pages, 12 figures and 10 tables. Submitted to a high-impact journal. The reduced spectra and photometry will be made available via the journal webpage and the WISeREP archive after the acceptance of the paper

Convolutional Neural Networks (CNNs) combine large amounts of parallelizable computation with frequent memory access. Field Programmable Gate Arrays (FPGAs) can achieve low latency and high throughput CNN inference by implementing dataflow accelerators that pipeline layer-specific hardware to implement an entire network. By implementing a different processing element for each CNN layer, these layer-pipelined accelerators can achieve high compute density, but having all layers processing in parallel requires high memory bandwidth. Traditionally this has been satisfied by storing all weights on chip, but this is infeasible for the largest CNNs, which are often those most in need of acceleration. In this work we augment a state-of-the-art dataflow accelerator (HPIPE) to leverage both High-Bandwidth Memory (HBM) and on-chip storage, enabling high performance layer-pipelined dataflow acceleration of large CNNs. Based on profiling results of HBM's latency and throughput against expected address patterns, we develop an algorithm to choose which weight buffers should be moved off chip and how deep the on-chip FIFOs to HBM should be to minimize compute unit stalling. We integrate the new hardware generation within the HPIPE domain-specific CNN compiler and demonstrate good bandwidth efficiency against theoretical limits. Compared to the best prior work we obtain speed-ups of at least 19.4x, 5.1x and 10.5x on ResNet-18, ResNet-50 and VGG-16 respectively.

Audio deepfake detection has become a pivotal task over the last couple of years, as many recent speech synthesis and voice cloning systems generate highly realistic speech samples, thus enabling their use in malicious activities. In this paper we address the issue of audio deepfake detection as it was set in the ASVspoof5 challenge. First, we benchmark ten types of pretrained representations and show that the self-supervised representations stemming from the wav2vec2 and wavLM families perform best. Of the two, wavLM is better when restricting the pretraining data to LibriSpeech, as required by the challenge rules. To further improve performance, we finetune the wavLM model for the deepfake detection task. We extend the ASVspoof5 dataset with samples from other deepfake detection datasets and apply data augmentation. Our final challenge submission consists of a late fusion combination of four models and achieves an equal error rate of 6.56% and 17.08% on the two evaluation sets., Comment: Accepted at ASVspoof Workshop 2024

The uncertainty of a quantum state is given by the composition of two components. The first is called the quantum component and is given by the probability distribution of an observable relative to the state. The second is the classical component which is an uncertainty function that is applied to the first component. We characterize uncertainty functions in terms of four axioms. We then study four examples called variance, entropy, geometric and sine uncertainty functions. The final section presents the general theory of state uncertainty., Comment: 15 pages

Enzyme design plays a crucial role in both industrial production and biology. However, this field faces challenges due to the lack of comprehensive benchmarks and the complexity of enzyme design tasks, leading to a dearth of systematic research. Consequently, computational enzyme design is relatively overlooked within the broader protein domain and remains in its early stages. In this work, we address these challenges by introducing MetaEnzyme, a staged and unified enzyme design framework. We begin by employing a cross-modal structure-to-sequence transformation architecture, as the feature-driven starting point to obtain initial robust protein representation. Subsequently, we leverage domain adaptive techniques to generalize specific enzyme design tasks under low-resource conditions. MetaEnzyme focuses on three fundamental low-resource enzyme redesign tasks: functional design (FuncDesign), mutation design (MutDesign), and sequence generation design (SeqDesign). Through novel unified paradigm and enhanced representation capabilities, MetaEnzyme demonstrates adaptability to diverse enzyme design tasks, yielding outstanding results. Wet lab experiments further validate these findings, reinforcing the efficacy of the redesign process., Comment: Accepted to ACM Multimedia 2024

Nitrogen is produced by CNO-cycling in massive stars, and can be ejected in significant amounts in supernova explosions. While in H-rich SNe, its [\ion{N}{II}] 6548, 6583 emission becomes obscured by strong H$\alpha$, in explosions of He stars, this nitrogen emission becomes more visible. We here explore the formation of this line, using the \texttt{SUMO} code to compute spectra for a grid of 1D models with parameterized mixing informed from new 2D simulations. Because the mass fraction of nitrogen in the ejecta decreases with larger He core masses, as more of the He/N zone gets processed by shell helium burning and is lost to winds, the [\ion{N}{II}] luminosity relative to the overall optical flux probes the He core mass. By comparing to large samples of data, we find that low-mass He cores ($M_{\rm preSN}\lesssim\ 3\ M_\odot$) are exclusively associated with Type IIb SNe, with the exception of Type Ib SN 2007Y. Seeing no strong nitrogen emission in other Type Ib SNe, the implication is either an origin from low-mass stars with the He/N layer (but not the He/C) layer peeled away, or from higher-mass He cores. We also see no clear nitrogen emission in Type Ic SNe. We discuss the diagnostic potential of this new line metric, and also dependencies on mass-loss-rate and metallicity., Comment: 17 pages, 11 figures + 12 pages appendix