PyTorchKR Papers

최신 논문

총 139,336편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2504.02607공식 코드 · Papers with Code

Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks

The practical deployment of learning-based autonomous systems would greatly benefit from tools that flexibly obtain safety guarantees in the form of certificate functions from data. While the geometrical properties of such certificate functions are well understood, synthesizing them using machine learning techniques still remains a challenge. To mitigate this issue, we propose a diffeomorphic function learning framework where prior structural knowledge of the desired output is encoded in the geometry of a simple surrogate function, which is subsequently augmented through an expressive, topology-preserving state-space transformation. Thereby, we achieve an indirect function approximation framework that is guaranteed to remain in the desired hypothesis space. To this end, we introduce a novel approach to construct diffeomorphic maps based on RBF networks, which facilitate precise, local transformations around data. Finally, we demonstrate our approach by learning diffeomorphic Lyapunov functions from real-world data and apply our method to different attractor systems.

arXiv:2504.02605공식 코드 · Papers with Code

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on Python, making them insufficient for evaluating Large Language Models (LLMs) across diverse software ecosystems. To address this, we introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering Java, TypeScript, JavaScript, Go, Rust, C, and C++. It includes a total of 1,632 high-quality instances, which were carefully annotated from 2,456 candidates by 68 expert annotators, ensuring that the benchmark can provide an accurate and reliable evaluation. Based on Multi-SWE-bench, we evaluate a series of state-of-the-art models using three representative methods (Agentless, SWE-agent, and OpenHands) and present a comprehensive analysis with key empirical insights. In addition, we launch a Multi-SWE-RL open-source community, aimed at building large-scale reinforcement learning (RL) training datasets for issue-resolving tasks. As an initial contribution, we release a set of 4,723 well-structured instances spanning seven programming languages, laying a solid foundation for RL research in this domain. More importantly, we open-source our entire data production pipeline, along with detailed tutorials, encouraging the open-source community to continuously contribute and expand the dataset. We envision our Multi-SWE-bench and the ever-growing Multi-SWE-RL community as catalysts for advancing RL toward its full potential, bringing us one step closer to the dawn of AGI.

arXiv:2504.02565공식 코드 · Papers with Code

MAD: A Magnitude And Direction Policy Parametrization for Stability Constrained Reinforcement Learning

We introduce magnitude and direction (MAD) policies, a policy parameterization for reinforcement learning (RL) that preserves Lp closed-loop stability for nonlinear dynamical systems. Although complete in their ability to describe all stabilizing controllers, methods based on nonlinear Youla and system-level synthesis are significantly affected by the difficulty of parameterizing Lp-stable operators. In contrast, MAD policies introduce explicit feedback on state-dependent features - a key element behind the success of RL pipelines - without compromising closed-loop stability. This is achieved by describing the magnitude of the control input with a disturbance-feedback Lp-stable operator, while selecting its direction based on state-dependent features through a universal function approximator. We further characterize the robust stability properties of MAD policies under model mismatch. Unlike existing disturbance-feedback policy parameterizations, MAD policies introduce state-feedback components compatible with model-free RL pipelines, ensuring closed-loop stability without requiring model information beyond open-loop stability. Numerical experiments show that MAD policies trained with deep deterministic policy gradient (DDPG) methods generalize to unseen scenarios, matching the performance of standard neural network policies while guaranteeing closed-loop stability by design.

arXiv:2504.02380공식 코드 · Papers with Code

Beyond Asymptotics: Targeted exploration with finite-sample guarantees

In this paper, we introduce a targeted exploration strategy for the non-asymptotic, finite-time case. The proposed strategy is applicable to uncertain linear time-invariant systems subject to sub-Gaussian disturbances. As the main result, the proposed approach provides a priori guarantees, ensuring that the optimized exploration inputs achieve a desired accuracy of the model parameters. The technical derivation of the strategy (i) leverages existing non-asymptotic identification bounds with self-normalized martingales, (ii) utilizes spectral lines to predict the effect of sinusoidal excitation, and (iii) effectively accounts for spectral transient error and parametric uncertainty. A numerical example illustrates how the finite exploration time influence the required exploration energy.

arXiv:2504.02362공식 코드 · Papers with Code

Brightness Perceiving for Recursive Low-Light Image Enhancement

Due to the wide dynamic range in real low-light scenes, there will be large differences in the degree of contrast degradation and detail blurring of captured images, making it difficult for existing end-to-end methods to enhance low-light images to normal exposure. To address the above issue, we decompose low-light image enhancement into a recursive enhancement task and propose a brightness-perceiving-based recursive enhancement framework for high dynamic range low-light image enhancement. Specifically, our recursive enhancement framework consists of two parallel sub-networks: Adaptive Contrast and Texture enhancement network (ACT-Net) and Brightness Perception network (BP-Net). The ACT-Net is proposed to adaptively enhance image contrast and details under the guidance of the brightness adjustment branch and gradient adjustment branch, which are proposed to perceive the degradation degree of contrast and details in low-light images. To adaptively enhance images captured under different brightness levels, BP-Net is proposed to control the recursive enhancement times of ACT-Net by exploring the image brightness distribution properties. Finally, in order to coordinate ACT-Net and BP-Net, we design a novel unsupervised training strategy to facilitate the training procedure. To further validate the effectiveness of the proposed method, we construct a new dataset with a broader brightness distribution by mixing three low-light datasets. Compared with eleven existing representative methods, the proposed method achieves new SOTA performance on six reference and no reference metrics. Specifically, the proposed method improves the PSNR by 0.9 dB compared to the existing SOTA method.

arXiv:2504.02277공식 코드 · Papers with Code

Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge Distillation

Medical imaging, particularly X-ray analysis, often involves detecting multiple conditions simultaneously within a single scan, making multi-label classification crucial for real-world clinical applications. We present the Medical X-ray Attention (MXA) block, a novel attention mechanism tailored specifically to address the unique challenges of X-ray abnormality detection. The MXA block enhances traditional Multi-Head Self Attention (MHSA) by integrating a specialized module that efficiently captures both detailed local information and broader global context. To the best of our knowledge, this is the first work to propose a task-specific attention mechanism for diagnosing chest X-rays, as well as to attempt multi-label classification using an Efficient Vision Transformer (EfficientViT). By embedding the MXA block within the EfficientViT architecture and employing knowledge distillation, our proposed model significantly improves performance on the CheXpert dataset, a widely used benchmark for multi-label chest X-ray abnormality detection. Our approach achieves an area under the curve (AUC) of 0.85, an absolute improvement of 0.19 compared to our baseline model's AUC of 0.66, corresponding to a substantial approximate 233% relative improvement over random guessing (AUC = 0.5).

arXiv:2504.02264공식 코드 · Papers with Code

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper proposes MMTL-UniAD, a unified multi-modal multi-task learning framework that simultaneously recognizes driver behavior (e.g., looking around, talking), driver emotion (e.g., anxiety, happiness), vehicle behavior (e.g., parking, turning), and traffic context (e.g., traffic jam, traffic smooth). A key challenge is avoiding negative transfer between tasks, which can impair learning performance. To address this, we introduce two key components into the framework: one is the multi-axis region attention network to extract global context-sensitive features, and the other is the dual-branch multimodal embedding to learn multimodal embeddings from both task-shared and task-specific features. The former uses a multi-attention mechanism to extract task-relevant features, mitigating negative transfer caused by task-unrelated features. The latter employs a dual-branch structure to adaptively adjust task-shared and task-specific parameters, enhancing cross-task knowledge transfer while reducing task conflicts. We assess MMTL-UniAD on the AIDE dataset, using a series of ablation studies, and show that it outperforms state-of-the-art methods across all four tasks. The code is available on https://github.com/Wenzhuo-Liu/MMTL-UniAD.

arXiv:2504.02259cs.CV공식 코드 · Papers with Code

Re-thinking Temporal Search for Long-Form Video Understanding

긴 형식 비디오 이해는 컴퓨터 비전 분야에서 여전히 중요한 도전 과제로 남아 있습니다. 이 연구에서는 시간 검색 패러다임을 재조명하고, 최신 비전-언어 모델(VLM)들이 직면한 근본적인 문제를 해결하기 위해 'Long Video Haystack' 문제로 정의합니다. 이는 수만 개의 프레임 중에서 특정 쿼리에 따라 최소한의 관련 프레임을 찾는 과정을 의미합니다. 이를 위해 저자들은 480시간의 비디오와 15,092개의 인간 주석 인스턴스를 포함하는 LV-HAYSTACK 데이터셋을 소개하여 시간 검색의 품질과 효율성을 개선하고자 합니다. LV-HAYSTACK의 결과는 현재의 최신 검색 방법들이 Longvideobench subset에서 2.1%의 시간 F1 점수만을 달성하고 있음을 보여줍니다. 또한, 저자들은 이미지에서의 시각적 검색에 영감을 받아 경량 시간 검색 프레임워크인 T*를 제안합니다. T*는 비용이 많이 드는 시간 검색을 공간 검색으로 재구성하여, 강력한 시각적 로컬라이제이션 기술을 활용하고 적응형 확대 메커니즘을 도입합니다. 이러한 접근 방식은 기존 방법들과 통합될 때 SOTA 성능을 크게 향상시키며, 32프레임의 추론 예산 하에서 GPT-4o의 성능을 50.5%에서 53.1%로, LLaVA-OneVision-OV-72B의 성능을 56.5%에서 62.4%로 개선하는 결과를 보여줍니다. 이 연구는 긴 형식 비디오 이해 시스템 개발에 중요한 기여를 하며, 향후 다중 모달 이해를 향상시키기 위한 가능성을 제시합니다.

arXiv:2504.02203공식 코드 · Papers with Code

Modelling \textit{Aedes albopictus} management, incorporating immigration and bi-directional \textit{Wolbachia} interactions

\textit{Aedes albopictus} mosquitoes are competent vectors for the spread of at least 24 different arboviruses, including dengue, Ross River, and Japanese encephalitis viruses. However, they remain less studied than their more urban cousins, \textit{Aedes aegypti}. We model an Incompatible Insect Technique (IIT) strategy for mosquito control, with bi-directional incompatibility between two strains of \textit{Wolbachia} (\walba/\walbb\, $\times$ \arwp) and age-based cytoplasmic incompatibility decay in a well-mixed population. An important consideration in bi-directional IIT control programs is reversibility when immigration is included. We explore the establishment probability after female contamination of an artificially-infected \textit{Wolbachia} mosquito strain, finding a conservative threshold of 40\% likely driven by mating inefficiencies -- this threshold needs validation in future field and lab experiments. We consider the suppression dynamics and probability of mosquito management success for different release strategies, showing differences in success between release cessation and six months later for different immigration rates. Importantly, our model suggests bi-directional IIT control programs are reversible with low amounts of immigration. We determine a corresponding cost proxy (numbers of mosquitoes released), showing similar short-term costs with differences in medium- and longer-term costs between release strategies. This work demonstrates opportunities to optimise the suppression of these medically important mosquitoes.

arXiv:2504.02160공식 코드 · Papers with Code

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

arXiv:2504.02147공식 코드 · Papers with Code

Data-Driven Nonconvex Reachability Analysis using Exact Multiplication

This paper addresses a fundamental challenge in data-driven reachability analysis: accurately representing and propagating non-convex reachable sets. We propose a novel approach using constrained polynomial zonotopes to describe reachable sets for unknown LTI systems. Unlike constrained zonotopes commonly used in existing literature, constrained polynomial zonotopes are closed under multiplication with constrained matrix zonotopes. We leverage this property to develop an exact multiplication method that preserves the non-convex geometry of reachable sets without resorting to approximations. We demonstrate that our approach provides tighter over-approximations of reachable sets for LTI systems compared to conventional methods.

arXiv:2504.02134공식 코드 · Papers with Code

Robust Channel Estimation for Optical Wireless Communications Using Neural Network

Optical Wireless Communication (OWC) has gained significant attention due to its high-speed data transmission and throughput. Optical wireless channels are often assumed to be flat, but we evaluate frequency selective channels to consider high data rate optical wireless or very dispersive environments. To address this for optical scenarios, this paper presents a robust channel estimation framework with low-complexity to mitigate frequency-selective effects, then to improve system reliability and performance. This channel estimation framework contains a neural network that can estimate general optical wireless channels without prior channel information about the environment. Based on this estimate and the corresponding delay spread, one of several candidate offline-trained neural networks will be activated to predict this channel. Simulation results demonstrate that the proposed method has improved and robust normalized mean square error (NMSE) and bit error rate (BER) performance compared to conventional estimation methods while maintaining computational efficiency. These findings highlight the potential of neural network solutions in enhancing the performance of OWC systems under indoor channel conditions.

arXiv:2504.01987공식 코드 · Papers with Code

CaLiV: LiDAR-to-Vehicle Calibration of Arbitrary Sensor Setups via Object Reconstruction

In autonomous systems, sensor calibration is essential for a safe and efficient navigation in dynamic environments. Accurate calibration is a prerequisite for reliable perception and planning tasks such as object detection and obstacle avoidance. Many existing LiDAR calibration methods require overlapping fields of view, while others use external sensing devices or postulate a feature-rich environment. In addition, Sensor-to-Vehicle calibration is not supported by the vast majority of calibration algorithms. In this work, we propose a novel target-based technique for extrinsic Sensor-to-Sensor and Sensor-to-Vehicle calibration of multi-LiDAR systems called CaLiV. This algorithm works for non-overlapping FoVs, as well as arbitrary calibration targets, and does not require any external sensing devices. First, we apply motion to produce FoV overlaps and utilize a simple unscented Kalman filter to obtain vehicle poses. Then, we use the Gaussian mixture model-based registration framework GMMCalib to align the point clouds in a common calibration frame. Finally, we reduce the task of recovering the sensor extrinsics to a minimization problem. We show that both translational and rotational Sensor-to-Sensor errors can be solved accurately by our method. In addition, all Sensor-to-Vehicle rotation angles can also be calibrated with high accuracy. We validate the simulation results in real-world experiments. The code is open source and available on https://github.com/TUMFTM/CaLiV.

arXiv:2504.01980공식 코드 · Papers with Code

Information Gain Is Not All You Need

Autonomous exploration in mobile robotics often involves a trade-off between two objectives: maximizing environmental coverage and minimizing the total path length. In the widely used information gain paradigm, exploration is guided by the expected value of observations. While this approach is effective under budget-constrained settings--where only a limited number of observations can be made--it fails to align with quality-constrained scenarios, in which the robot must fully explore the environment to a desired level of certainty or quality. In such cases, total information gain is effectively fixed, and maximizing it per step can lead to inefficient, greedy behavior and unnecessary backtracking. This paper argues that information gain should not serve as an optimization objective in quality-constrained exploration. Instead, it should be used to filter viable candidate actions. We propose a novel heuristic, distance advantage, which selects candidate frontiers based on a trade-off between proximity to the robot and remoteness from other frontiers. This heuristic aims to reduce future detours by prioritizing exploration of isolated regions before the robot's opportunity to visit them efficiently has passed. We evaluate our method in simulated environments against classical frontier-based exploration and gain-maximizing approaches. Results show that distance advantage significantly reduces total path length across a variety of environments, both with and without access to prior map predictions. Our findings challenge the assumption that more accurate gain estimation improves performance and offer a more suitable alternative for the quality-constrained exploration paradigm.

arXiv:2504.01979공식 코드 · Papers with Code

Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data

With the rise of social media and Location-Based Social Networks (LBSN), check-in data across platforms has become crucial for User Identity Linkage (UIL). These data not only reveal users' spatio-temporal information but also provide insights into their behavior patterns and interests. However, cross-platform identity linkage faces challenges like poor data quality, high sparsity, and noise interference, which hinder existing methods from extracting cross-platform user information. To address these issues, we propose a Correlation-Attention Masked Transformer for User Identity Linkage Network (MT-Link), a transformer-based framework to enhance model performance by learning spatio-temporal co-occurrence patterns of cross-platform users. Our model effectively captures spatio-temporal co-occurrence in cross-platform user check-in sequences. It employs a correlation attention mechanism to detect the spatio-temporal co-occurrence between user check-in sequences. Guided by attention weight maps, the model focuses on co-occurrence points while filtering out noise, ultimately improving classification performance. Experimental results show that our model significantly outperforms state-of-the-art baselines by 12.92%~17.76% and 5.80%~8.38% improvements in terms of Macro-F1 and Area Under Curve (AUC).

arXiv:2504.02778공식 코드 · Papers with Code

Multi-Head Adaptive Graph Convolution Network for Sparse Point Cloud-Based Human Activity Recognition

Human activity recognition is increasingly vital for supporting independent living, particularly for the elderly and those in need of assistance. Domestic service robots with monitoring capabilities can enhance safety and provide essential support. Although image-based methods have advanced considerably in the past decade, their adoption remains limited by concerns over privacy and sensitivity to low-light or dark conditions. As an alternative, millimetre-wave (mmWave) radar can produce point cloud data which is privacy-preserving. However, processing the sparse and noisy point clouds remains a long-standing challenge. While graph-based methods and attention mechanisms show promise, they predominantly rely on "fixed" kernels; kernels that are applied uniformly across all neighbourhoods, highlighting the need for adaptive approaches that can dynamically adjust their kernels to the specific geometry of each local neighbourhood in point cloud data. To overcome this limitation, we introduce an adaptive approach within the graph convolutional framework. Instead of a single shared weight function, our Multi-Head Adaptive Kernel (MAK) module generates multiple dynamic kernels, each capturing different aspects of the local feature space. By progressively refining local features while maintaining global spatial context, our method enables convolution kernels to adapt to varying local features. Experimental results on benchmark datasets confirm the effectiveness of our approach, achieving state-of-the-art performance in human activity recognition. Our source code is made publicly available at: https://github.com/Gbouna/MAK-GCN

arXiv:2504.02767공식 코드 · Papers with Code

How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?

The spread of scientific knowledge depends on how researchers discover and cite previous work. The adoption of large language models (LLMs) in the scientific research process introduces a new layer to these citation practices. However, it remains unclear to what extent LLMs align with human citation practices, how they perform across domains, and may influence citation dynamics. Here, we show that LLMs systematically reinforce the Matthew effect in citations by consistently favoring highly cited papers when generating references. This pattern persists across scientific domains despite significant field-specific variations in existence rates, which refer to the proportion of generated references that match existing records in external bibliometric databases. Analyzing 274,951 references generated by GPT-4o for 10,000 papers, we find that LLM recommendations diverge from traditional citation patterns by preferring more recent references with shorter titles and fewer authors. Emphasizing their content-level relevance, the generated references are semantically aligned with the content of each paper at levels comparable to the ground truth references and display similar network effects while reducing author self-citations. These findings illustrate how LLMs may reshape citation practices and influence the trajectory of scientific discovery by reflecting and amplifying established trends. As LLMs become more integrated into the scientific research process, it is important to understand their role in shaping how scientific communities discover and build upon prior work.

arXiv:2504.02701공식 코드 · Papers with Code

Responsible Development of Offensive AI

As AI advances, broader consensus is needed to determine research priorities. This endeavor discusses offensive AI and provides guidance by leveraging Sustainable Development Goals (SDGs) and interpretability techniques. The objective is to more effectively establish priorities that balance societal benefits against risks. The two forms of offensive AI evaluated in this study are vulnerability detection agents, which solve Capture- The-Flag challenges, and AI-powered malware.

arXiv:2504.02542공식 코드 · Papers with Code

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

Talking head synthesis is vital for virtual avatars and human-computer interaction. However, most existing methods are typically limited to accepting control from a single primary modality, restricting their practical utility. To this end, we introduce \textbf{ACTalker}, an end-to-end video diffusion framework that supports both multi-signals control and single-signal control for talking head video generation. For multiple control, we design a parallel mamba structure with multiple branches, each utilizing a separate driving signal to control specific facial regions. A gate mechanism is applied across all branches, providing flexible control over video generation. To ensure natural coordination of the controlled video both temporally and spatially, we employ the mamba structure, which enables driving signals to manipulate feature tokens across both dimensions in each branch. Additionally, we introduce a mask-drop strategy that allows each driving signal to independently control its corresponding facial region within the mamba structure, preventing control conflicts. Experimental results demonstrate that our method produces natural-looking facial videos driven by diverse signals and that the mamba layer seamlessly integrates multiple driving modalities without conflict.

arXiv:2504.02508공식 코드 · Papers with Code

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops when quantized for practical deployment, particularly by post-training quantization (PTQ) under ultra-low bits. Recently, reconstruction-based PTQ methods have shown promising performance in quantizing Convolutional Neural Networks (CNNs). However, they fail when applied to ViTs, primarily due to the inaccurate estimation of output importance and the substantial accuracy degradation in quantizing post-GELU activations. To address these issues, we propose \textbf{APHQ-ViT}, a novel PTQ approach based on importance estimation with Average Perturbation Hessian (APH). Specifically, we first thoroughly analyze the current approximation approaches with Hessian loss, and propose an improved average perturbation Hessian loss. To deal with the quantization of the post-GELU activations, we design an MLP Reconstruction (MR) method by replacing the GELU function in MLP with ReLU and reconstructing it by the APH loss on a small unlabeled calibration set. Extensive experiments demonstrate that APHQ-ViT using linear quantizers outperforms existing PTQ methods by substantial margins in 3-bit and 4-bit across different vision tasks. The source code is available at https://github.com/GoatWu/APHQ-ViT.