PyTorchKR Papers

최신 논문

총 139,336편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2504.19538공식 코드 · Papers with Code

Towards Faster and More Compact Foundation Models for Molecular Property Prediction

Advancements in machine learning for molecular property prediction have improved accuracy but at the expense of higher computational cost and longer training times. Recently, the Joint Multi-domain Pre-training (JMP) foundation model has demonstrated strong performance across various downstream tasks with reduced training time over previous models. Despite JMP's advantages, fine-tuning it on molecular datasets ranging from small-scale to large-scale requires considerable time and computational resources. In this work, we investigate strategies to enhance efficiency by reducing model size while preserving performance. To better understand the model's efficiency, we analyze the layer contributions of JMP and find that later interaction blocks provide diminishing returns, suggesting an opportunity for model compression. We explore block reduction strategies by pruning the pre-trained model and evaluating its impact on efficiency and accuracy during fine-tuning. Our analysis reveals that removing two interaction blocks results in a minimal performance drop, reducing the model size by 32% while increasing inference throughput by 1.3x. These results suggest that JMP-L is over-parameterized and that a smaller, more efficient variant can achieve comparable performance with lower computational cost. Our study provides insights for developing lighter, faster, and more scalable foundation models for molecular and materials discovery. The code is publicly available at: https://github.com/Yasir-Ghunaim/efficient-jmp.

arXiv:2504.18554공식 코드 · Papers with Code

An X-ray absorption spectrum database for iron-containing proteins

Earth-abundant iron is an essential metal in regulating the structure and function of proteins. This study presents the development of a comprehensive X-ray Absorption Spectroscopy (XAS) database focused on iron-containing proteins, addressing a critical gap in available high-quality annotated spectral data for iron-containing proteins. The database integrates detailed XAS spectra with their corresponding local structural data of proteins and enables a direct comparison of spectral features and structural motifs. Utilizing a combination of manual curation and semi-automated data extraction techniques, we developed a comprehensive dataset from an extensive review of literature, ensuring the quality and accuracy of data, which contains 437 protein structures and 1954 XAS spectrums. Our methods included careful documentation and validation processes to ensure accuracy and reproducibility. This dataset not only centralizes information on iron-containing proteins but also supports advanced data-driven discoveries, such as machine learning, to predict and analyze protein structure and functions. This work underscores the potential of integrating detailed spectroscopic data with structural biology to advance the field of biological chemistry and catalysis.

arXiv:2504.17860공식 코드 · Papers with Code

An Integrated Genomics Workflow Tool: Simulating Reads, Evaluating Read Alignments, and Optimizing Variant Calling Algorithms

Next-generation sequencing (NGS) is a pivotal technique in genome sequencing due to its high throughput, rapid results, cost-effectiveness, and enhanced accuracy. Its significance extends across various domains, playing a crucial role in identifying genetic variations and exploring genomic complexity. NGS finds applications in diverse fields such as clinical genomics, comparative genomics, functional genomics, and metagenomics, contributing substantially to advancements in research, medicine, and scientific disciplines. Within the sphere of genomics data science, the execution of read simulation, mapping, and variant calling holds paramount importance for obtaining precise and dependable results. Given the plethora of tools available for these purposes, each employing distinct methodologies and options, a nuanced understanding of their intricacies becomes imperative for optimization. This research, situated at the intersection of data science and genomics, involves a meticulous assessment of various tools, elucidating their individual strengths and weaknesses through rigorous experimentation and analysis. This comprehensive evaluation has enabled the researchers to pinpoint the most accurate tools, reinforcing the alignment between the established workflow and the demonstrated efficacy of specific tools in the context of genomics data analysis. To meet these requirements, "VarFind", an open-source and freely accessible pipeline tool designed to automate the entire process has been introduced (VarFind GitHub repository: https://github.com/shanikawm/varfinder)

arXiv:2504.16152공식 코드 · Papers with Code

Heterogeneous networks in drug-target interaction prediction

Drug discovery requires a tremendous amount of time and cost. Computational drug-target interaction prediction, a significant part of this process, can reduce these requirements by narrowing the search space for wet lab experiments. In this survey, we provide comprehensive details of graph machine learning-based methods in predicting drug-target interaction, as they have shown promising results in this field. These details include the overall framework, main contribution, datasets, and their source codes. The selected papers were mainly published from 2020 to 2024. Prior to discussing papers, we briefly introduce the datasets commonly used with these methods and measurements to assess their performance. Finally, future challenges and some crucial areas that need to be explored are discussed.

arXiv:2504.16143공식 코드 · Papers with Code

A Statistical Approach for Synthetic EEG Data Generation

Electroencephalogram (EEG) data is crucial for diagnosing mental health conditions but is costly and time-consuming to collect at scale. Synthetic data generation offers a promising solution to augment datasets for machine learning applications. However, generating high-quality synthetic EEG that preserves emotional and mental health signals remains challenging. This study proposes a method combining correlation analysis and random sampling to generate realistic synthetic EEG data. We first analyze interdependencies between EEG frequency bands using correlation analysis. Guided by this structure, we generate synthetic samples via random sampling. Samples with high correlation to real data are retained and evaluated through distribution analysis and classification tasks. A Random Forest model trained to distinguish synthetic from real EEG performs at chance level, indicating high fidelity. The generated synthetic data closely match the statistical and structural properties of the original EEG, with similar correlation coefficients and no significant differences in PERMANOVA tests. This method provides a scalable, privacy-preserving approach for augmenting EEG datasets, enabling more efficient model training in mental health research.

arXiv:2504.15514공식 코드 · Papers with Code

Learning-Based Two-Way Communications: Algorithmic Framework and Comparative Analysis

Machine learning (ML)-based feedback channel coding has garnered significant research interest in the past few years. However, there has been limited research exploring ML approaches in the so-called "two-way" setting where two users jointly encode messages and feedback for each other over a shared channel. In this work, we present a general architecture for ML-based two-way feedback coding, and show how several popular one-way schemes can be converted to the two-way setting through our framework. We compare such schemes against their one-way counterparts, revealing error-rate benefits of ML-based two-way coding in certain signal-to-noise ratio (SNR) regimes. We then analyze the tradeoffs between error performance and computational overhead for three state-of-the-art neural network coding models instantiated in the two-way paradigm.

arXiv:2505.01074공식 코드 · Papers with Code

WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks

The rapid evolution of wireless networks presents unprecedented challenges in managing complex and dynamic systems. Existing methods are increasingly facing fundamental limitations in addressing these challenges. In this paper, we introduce WirelessAgent, a novel framework that harnesses large language models (LLMs) to create autonomous AI agents for diverse wireless network tasks. This framework integrates four core modules that mirror human cognitive processes: perception, memory, planning, and action. To implement it, we provide a basic usage based on agentic workflows and the LangGraph architecture. We demonstrate the effectiveness of WirelessAgent through a comprehensive case study on network slicing. The numerical results show that WirelessAgent achieves $44.4\%$ higher bandwidth utilization than the \emph{Prompt-based} method, while performing only $4.3\%$ below the \emph{Rule-based optimality}. Notably, WirelessAgent delivers near-optimal network throughput across diverse network scenarios. These underscore the framework's potential for intelligent and autonomous resource management in future wireless networks. The code is available at \url{https://github.com/jwentong/WirelessAgent_R1}.

arXiv:2504.21209공식 코드 · Papers with Code

Generalised Label-free Artefact Cleaning for Real-time Medical Pulsatile Time Series

Artefacts compromise clinical decision-making in the use of medical time series. Pulsatile waveforms offer probabilities for accurate artefact detection, yet most approaches rely on supervised manners and overlook patient-level distribution shifts. To address these issues, we introduce a generalised label-free framework, GenClean, for real-time artefact cleaning and leverage an in-house dataset of 180,000 ten-second arterial blood pressure (ABP) samples for training. We first investigate patient-level generalisation, demonstrating robust performances under both intra- and inter-patient distribution shifts. We further validate its effectiveness through challenging cross-disease cohort experiments on the MIMIC-III database. Additionally, we extend our method to photoplethysmography (PPG), highlighting its applicability to diverse medical pulsatile signals. Finally, its integration into ICM+, a clinical research monitoring software, confirms the real-time feasibility of our framework, emphasising its practical utility in continuous physiological monitoring. This work provides a foundational step toward precision medicine in improving the reliability of high-resolution medical time series analysis

arXiv:2504.20580공식 코드 · Papers with Code

Sense-then-Charge: Wireless Power Transfer to Unresponsive Devices with Unknown Location

This paper explores a multi-antenna dual-functional radio frequency (RF) wireless power transfer (WPT) and radar system to charge multiple unresponsive devices. We formulate a beamforming problem to maximize the minimum received power at the devices without prior location and channel state information (CSI) knowledge. We propose dividing transmission blocks into sensing and charging phases. First, the location of the devices is estimated by sending sensing signals and performing multiple signal classification and least square estimation on the received echo. Then, the estimations are used for CSI prediction and RF-WPT beamforming. Simulation results reveal that there is an optimal number of blocks allocated for sensing and charging depending on the system setup. Our sense-then-charge (STC) protocol can outperform CSI-free benchmarks and achieve near-optimal performance with a sufficient number of receive antennas and transmit power. However, STC struggles if using insufficient antennas or power as device numbers grow.

arXiv:2504.19639공식 코드 · Papers with Code

A Unified Benchmark of Federated Learning with Kolmogorov-Arnold Networks for Medical Imaging

Federated Learning (FL) enables model training across decentralized devices without sharing raw data, thereby preserving privacy in sensitive domains like healthcare. In this paper, we evaluate Kolmogorov-Arnold Networks (KAN) architectures against traditional MLP across six state-of-the-art FL algorithms on a blood cell classification dataset. Notably, our experiments demonstrate that KAN can effectively replace MLP in federated environments, achieving superior performance with simpler architectures. Furthermore, we analyze the impact of key hyperparameters-grid size and network architecture-on KAN performance under varying degrees of Non-IID data distribution. Additionally, our ablation studies reveal that optimizing KAN width while maintaining minimal depth yields the best performance in federated settings. As a result, these findings establish KAN as a promising alternative for privacy-preserving medical imaging applications in distributed healthcare. To the best of our knowledge, this is the first comprehensive benchmark of KAN in FL settings for medical imaging task.

arXiv:2504.19408공식 코드 · Papers with Code

UNet with Axial Transformer : A Neural Weather Model for Precipitation Nowcasting

Making accurate weather predictions can be particularly challenging for localized storms or events that evolve on hourly timescales, such as thunderstorms. Hence, our goal for the project was to model Weather Nowcasting for making highly localized and accurate predictions that apply to the immediate future replacing the current numerical weather models and data assimilation systems with Deep Learning approaches. A significant advantage of machine learning is that inference is computationally cheap given an already-trained model, allowing forecasts that are nearly instantaneous and in the native high resolution of the input data. In this work we developed a novel method that employs Transformer-based machine learning models to forecast precipitation. This approach works by leveraging axial attention mechanisms to learn complex patterns and dynamics from time series frames. Moreover, it is a generic framework and can be applied to univariate and multivariate time series data, as well as time series embeddings data. This paper represents an initial research on the dataset used in the domain of next frame prediciton, and hence, we demonstrate state-of-the-art results in terms of metrices (PSNR = 47.67, SSIM = 0.9943) used for the given dataset using UNet with Axial Transformer.

arXiv:2504.19000공식 코드 · Papers with Code

Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizers

Machine learning (ML) models are often sensitive to carefully crafted yet seemingly unnoticeable perturbations. Such adversarial examples are considered to be a property of ML models, often associated with their black-box operation and sensitivity to features learned from data. This work examines the adversarial sensitivity of non-learned decision rules, and particularly of iterative optimizers. Our analysis is inspired by the recent developments in deep unfolding, which cast such optimizers as ML models. We show that non-learned iterative optimizers share the sensitivity to adversarial examples of ML models, and that attacking iterative optimizers effectively alters the optimization objective surface in a manner that modifies the minima sought. We then leverage the ability to cast iteration-limited optimizers as ML models to enhance robustness via adversarial training. For a class of proximal gradient optimizers, we rigorously prove how their learning affects adversarial sensitivity. We numerically back our findings, showing the vulnerability of various optimizers, as well as the robustness induced by unfolding and adversarial training.

arXiv:2505.01388공식 코드 · Papers with Code

Potential Contrast: Properties, Equivalences, and Generalization to Multiple Classes

Potential contrast is typically used as an image quality measure and quantifies the maximal possible contrast between samples from two classes of pixels in an image after an arbitrary grayscale transformation. It has been valuable in cultural heritage applications, identifying and visualizing relevant information in multispectral images while requiring a small number of pixels to be manually sampled. In this work, we introduce a normalized version of potential contrast that removes dependence on image format and also prove equalities that enable generalization to more than two classes and to continuous settings. Finally, we exemplify the utility of multi-class normalized potential contrast through an application to a medieval music manuscript with visible bleedthrough from the back page. We share our implementations, based on both original algorithms and our new equalities, including generalization to multiple classes, at https://github.com/wallacepeaslee/Multiple-Class-Normalized-Potential-Contrast.

arXiv:2505.00737공식 코드 · Papers with Code

A Survey on 3D Reconstruction Techniques in Plant Phenotyping: From Classical Methods to Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and Beyond

Plant phenotyping plays a pivotal role in understanding plant traits and their interactions with the environment, making it crucial for advancing precision agriculture and crop improvement. 3D reconstruction technologies have emerged as powerful tools for capturing detailed plant morphology and structure, offering significant potential for accurate and automated phenotyping. This paper provides a comprehensive review of the 3D reconstruction techniques for plant phenotyping, covering classical reconstruction methods, emerging Neural Radiance Fields (NeRF), and the novel 3D Gaussian Splatting (3DGS) approach. Classical methods, which often rely on high-resolution sensors, are widely adopted due to their simplicity and flexibility in representing plant structures. However, they face challenges such as data density, noise, and scalability. NeRF, a recent advancement, enables high-quality, photorealistic 3D reconstructions from sparse viewpoints, but its computational cost and applicability in outdoor environments remain areas of active research. The emerging 3DGS technique introduces a new paradigm in reconstructing plant structures by representing geometry through Gaussian primitives, offering potential benefits in both efficiency and scalability. We review the methodologies, applications, and performance of these approaches in plant phenotyping and discuss their respective strengths, limitations, and future prospects (https://github.com/JiajiaLi04/3D-Reconstruction-Plants). Through this review, we aim to provide insights into how these diverse 3D reconstruction techniques can be effectively leveraged for automated and high-throughput plant phenotyping, contributing to the next generation of agricultural technology.

arXiv:2505.00735공식 코드 · Papers with Code

Leveraging Depth Maps and Attention Mechanisms for Enhanced Image Inpainting

Existing deep learning-based image inpainting methods typically rely on convolutional networks with RGB images to reconstruct images. However, relying exclusively on RGB images may neglect important depth information, which plays a critical role in understanding the spatial and structural context of a scene. Just as human vision leverages stereo cues to perceive depth, incorporating depth maps into the inpainting process can enhance the model's ability to reconstruct images with greater accuracy and contextual awareness. In this paper, we propose a novel approach that incorporates both RGB and depth images for enhanced image inpainting. Our models employ a dual encoder architecture, where one encoder processes the RGB image and the other handles the depth image. The encoded features from both encoders are then fused in the decoder using an attention mechanism, effectively integrating the RGB and depth representations. We use two different masking strategies, line and square, to test the robustness of the model under different types of occlusions. To further analyze the effectiveness of our approach, we use Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations to examine the regions of interest the model focuses on during inpainting. We show that incorporating depth information alongside the RGB image significantly improves the reconstruction quality. Through both qualitative and quantitative comparisons, we demonstrate that the depth-integrated model outperforms the baseline, with attention mechanisms further enhancing inpainting performance, as evidenced by multiple evaluation metrics and visualization.

arXiv:2505.00045공식 코드 · Papers with Code

Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising

Noise synthesis is a promising solution for addressing the data shortage problem in data-driven low-light RAW image denoising. However, accurate noise synthesis methods often necessitate labor-intensive calibration and profiling procedures during preparation, preventing them from landing to practice at scale. This work introduces a practically simple noise synthesis pipeline based on detailed analyses of noise properties and extensive justification of widespread techniques. Compared to other approaches, our proposed pipeline eliminates the cumbersome system gain calibration and signal-independent noise profiling steps, reducing the preparation time for noise synthesis from days to hours. Meanwhile, our method exhibits strong denoising performance, showing an up to 0.54dB PSNR improvement over the current state-of-the-art noise synthesis technique. Code is released at https://github.com/SonyResearch/raw_image_denoising

arXiv:2504.20479공식 코드 · Papers with Code

Full-field surrogate modeling of cardiac function encoding geometric variability

Combining physics-based modeling with data-driven methods is critical to enabling the translation of computational methods to clinical use in cardiology. The use of rigorous differential equations combined with machine learning tools allows for model personalization with uncertainty quantification in time frames compatible with clinical practice. However, accurate and efficient surrogate models of cardiac function, built from physics-based numerical simulation, are still mostly geometry-specific and require retraining for different patients and pathological conditions. We propose a novel computational pipeline to embed cardiac anatomies into full-field surrogate models. We generate a dataset of electrophysiology simulations using a complex multi-scale mathematical model coupling partial and ordinary differential equations. We adopt Branched Latent Neural Maps (BLNMs) as an effective scientific machine learning method to encode activation maps extracted from physics-based numerical simulations into a neural network. Leveraging large deformation diffeomorphic metric mappings, we build a biventricular anatomical atlas and parametrize the anatomical variability of a small and challenging cohort of 13 pediatric patients affected by Tetralogy of Fallot. We propose a novel statistical shape modeling based z-score sampling approach to generate a new synthetic cohort of 52 biventricular geometries that are compatible with the original geometrical variability. This synthetic cohort acts as the training set for BLNMs. Our surrogate model demonstrates robustness and great generalization across the complex original patient cohort, achieving an average adimensional mean squared error of 0.0034. The Python implementation of our BLNM model is publicly available under MIT License at https://github.com/StanfordCBCL/BLNM.

arXiv:2504.20108공식 코드 · Papers with Code

Swapped Logit Distillation via Bi-level Teacher Alignment

Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its original distribution, which can possibly lead to incorrect predictions. In this article, we propose a logit-based distillation via swapped logit processing, namely Swapped Logit Distillation (SLD). SLD is proposed under two assumptions: (1) the wrong prediction occurs when the prediction label confidence is not the maximum; (2) the "natural" limit of probability remains uncertain as the best value addition to the target cannot be determined. To address these issues, we propose a swapped logit processing scheme. Through this approach, we find that the swap method can be effectively extended to teacher and student outputs, transforming into two teachers. We further introduce loss scheduling to boost the performance of two teachers' alignment. Extensive experiments on image classification tasks demonstrate that SLD consistently performs best among previous state-of-the-art methods.

arXiv:2504.20073공식 코드 · Papers with Code

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in static tasks, multi-turn agent RL training remains underexplored. We propose StarPO (State-Thinking-Actions-Reward Policy Optimization), a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents. Our study on three stylized environments reveals three core findings. First, our agent RL training shows a recurring mode of Echo Trap where reward variance cliffs and gradient spikes; we address this with StarPO-S, a stabilized variant with trajectory filtering, critic incorporation, and decoupled clipping. Second, we find the shaping of RL rollouts would benefit from diverse initial states, medium interaction granularity and more frequent sampling. Third, we show that without fine-grained, reasoning-aware reward signals, agent reasoning hardly emerge through multi-turn RL and they may show shallow strategies or hallucinated thoughts. Code and environments are available at https://github.com/RAGEN-AI/RAGEN.

arXiv:2504.19589공식 코드 · Papers with Code

Magnifier: A Multi-grained Neural Network-based Architecture for Burned Area Delineation

In crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural networks are able to analyze satellite acquisitions and determine which areas were affected by a catastrophic event. The problem in their development in this context is the data scarcity and the lack of extensive benchmark datasets, limiting the capabilities of training large neural network models. In this paper, we propose a novel methodology, namely Magnifier, to improve segmentation performance with limited data availability. The Magnifier methodology is applicable to any existing encoder-decoder architecture, as it extends a model by merging information at different contextual levels through a dual-encoder approach: a local and global encoder. Magnifier analyzes the input data twice using the dual-encoder approach. In particular, the local and global encoders extract information from the same input at different granularities. This allows Magnifier to extract more information than the other approaches given the same set of input images. Magnifier improves the quality of the results of +2.65% on average IoU while leading to a restrained increase in terms of the number of trainable parameters compared to the original model. We evaluated our proposed approach with state-of-the-art burned area segmentation models, demonstrating, on average, comparable or better performances in less than half of the GFLOPs.