PyTorchKR Papers

최신 논문

총 139,333편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2505.08345공식 코드 · Papers with Code

SHAP-based Explanations are Sensitive to Feature Representation

Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data engineering techniques, such as representing age with a histogram or encoding race in a specific way, can manipulate feature importance as determined by popular methods like SHAP. Notably, the sensitivity of explanations to feature representation can be exploited by adversaries to obscure issues like discrimination. While the intuition behind these results is straightforward, their systematic exploration has been lacking. Previous work has focused on adversarial attacks on feature-based explainers by biasing data or manipulating models. To the best of our knowledge, this is the first study demonstrating that explainers can be misled by standard, seemingly innocuous data engineering techniques.

arXiv:2505.08341공식 코드 · Papers with Code

Benchmarking AI scientists in omics data-driven biological research

The rise of large language models and multi-agent systems has sparked growing interest in AI scientists capable of autonomous biological research. However, existing benchmarks either focus on reasoning without data or on data analysis with predefined statistical answers, lacking realistic, data-driven evaluation settings. Here, we introduce the Biological AI Scientist Benchmark (BaisBench), a benchmark designed to assess AI scientists' ability to generate biological discoveries through data analysis and reasoning with external knowledge. BaisBench comprises two tasks: cell type annotation on 31 expert-labeled single-cell datasets, and scientific discovery through answering 198 multiple-choice questions derived from the biological insights of 41 recent single-cell studies. Systematic experiments on state-of-the-art AI scientists and LLM agents showed that while promising, current models still substantially underperform human experts on both tasks. We hope BaisBench will fill this gap and serve as a foundation for advancing and evaluating AI models for scientific discovery. The benchmark can be found at: https://github.com/EperLuo/BaisBench.

arXiv:2505.08037공식 코드 · Papers with Code

TiSpell: A Semi-Masked Methodology for Tibetan Spelling Correction covering Multi-Level Error with Data Augmentation

Multi-level Tibetan spelling correction addresses errors at both the character and syllable levels within a unified model. Existing methods focus mainly on single-level correction and lack effective integration of both levels. Moreover, there are no open-source datasets or augmentation methods tailored for this task in Tibetan. To tackle this, we propose a data augmentation approach using unlabeled text to generate multi-level corruptions, and introduce TiSpell, a semi-masked model capable of correcting both character- and syllable-level errors. Although syllable-level correction is more challenging due to its reliance on global context, our semi-masked strategy simplifies this process. We synthesize nine types of corruptions on clean sentences to create a robust training set. Experiments on both simulated and real-world data demonstrate that TiSpell, trained on our dataset, outperforms baseline models and matches the performance of state-of-the-art approaches, confirming its effectiveness.

arXiv:2505.07841공식 코드 · Papers with Code

Token Communication-Driven Multimodal Large Models in Resource-Constrained Multiuser Networks

The proliferation of intelligent applications at the wireless edge, alongside the exponential growth of multimodal data, poses challenges for deploying multimodal large models (MLMs) in resource-constrained networks. These constraints manifest as limited bandwidth, computational capacity, and stringent latency requirements, particularly under low signal-to-noise ratio (SNR) conditions. To overcome these limitations, we propose a token communication paradigm that facilitates the decentralized deployment of MLMs across user devices and edge infrastructure (e.g., base stations). In this paradigm, task-relevant tokens are extracted from multimodal inputs and serve as the primary medium for communication between distributed model components. To align semantics and optimize transmission efficiency, we propose a dual-pronged approach: 1) We design a contrastive split fine-tuning method to project heterogeneous modalities into a shared feature space, enabling seamless interaction between model components while preserving modal-specific semantics. 2) We employ a lightweight compression technique to reduce the size of transmitted tokens, minimizing bandwidth consumption without sacrificing task-critical information. The proposed framework integrates collaborative fine-tuning of both the foundation model and multimodal transceivers, ensuring that token generation and utilization are tailored to specific downstream tasks. Simulation experiments conducted under different SNR conditions demonstrate that our method results in a $13.7\%$ improvement in test accuracy. Furthermore, our approach exhibits quicker convergence rates, even with reduced token lengths, highlighting the promise of token communication for facilitating more scalable and resilient MLM implementations in practical multiuser networks.

arXiv:2505.07730공식 코드 · Papers with Code

Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction

Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search. A recent advance in VDR was introduced by ColPali, which significantly improved retrieval effectiveness through a late interaction mechanism. ColPali's approach demonstrated substantial performance gains over existing baselines that do not use late interaction on an established benchmark. In this study, we investigate the reproducibility and replicability of VDR methods with and without late interaction mechanisms by systematically evaluating their performance across multiple pre-trained vision-language models. Our findings confirm that late interaction yields considerable improvements in retrieval effectiveness; however, it also introduces computational inefficiencies during inference. Additionally, we examine the adaptability of VDR models to textual inputs and assess their robustness across text-intensive datasets within the proposed benchmark, particularly when scaling the indexing mechanism. Furthermore, our research investigates the specific contributions of late interaction by looking into query-patch matching in the context of visual document retrieval. We find that although query tokens cannot explicitly match image patches as in the text retrieval scenario, they tend to match the patch contains visually similar tokens or their surrounding patches.

arXiv:2505.07577공식 코드 · Papers with Code

From raw affiliations to organization identifiers

Accurate affiliation matching, which links affiliation strings to standardized organization identifiers, is critical for improving research metadata quality, facilitating comprehensive bibliometric analyses, and supporting data interoperability across scholarly knowledge bases. Existing approaches fail to handle the complexity of affiliation strings that often include mentions of multiple organizations or extraneous information. In this paper, we present AffRo, a novel approach designed to address these challenges, leveraging advanced parsing and disambiguation techniques. We also introduce AffRoDB, an expert-curated dataset to systematically evaluate affiliation matching algorithms, ensuring robust benchmarking. Results demonstrate the effectiveness of AffRp in accurately identifying organizations from complex affiliation strings.

arXiv:2505.07399공식 코드 · Papers with Code

Towards Autonomous 1/8th Offroad RC Racing -- The TruggySense Educational Platform

This paper presents a state-of-the-art Data Acquisition System designed for off-road conditions, deployed on a Team Corally Kagama 1/8 Remote Controlled Vehicle. The system is intended to support Advanced Driver Assistance Systems in an educational context by providing valuable, consistent, and representative data. Key measurement systems are discussed to enable insights into the Remote Controlled Vehicles stability during and after off-road races. Furthermore, four experiments where conducted to evaluate the Data Acquisition Systems accuracy, stability, and consistency in replicating real-world vehicle behavior. The proposed Data Acquisition System platform serves as a solid foundation for use in engineering education, enabling integration with various Advanced Driver Assistance Systems algorithms to enhance vehicle control and overall performance, offering a new dimension to off-road racing. Additionally, realtime telemetry enables verification and validation of Advanced Driver Assistance Systems algorithms based on the live operating state of the Radio Controlled Vehicle during races

arXiv:2505.06295공식 코드 · Papers with Code

Benchmarking Traditional Machine Learning and Deep Learning Models for Fault Detection in Power Transformers

Accurate diagnosis of power transformer faults is essential for ensuring the stability and safety of electrical power systems. This study presents a comparative analysis of conventional machine learning (ML) algorithms and deep learning (DL) algorithms for fault classification of power transformers. Using a condition-monitored dataset spanning 10 months, various gas concentration features were normalized and used to train five ML classifiers: Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Random Forest (RF), XGBoost, and Artificial Neural Network (ANN). In addition, four DL models were evaluated: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), One-Dimensional Convolutional Neural Network (1D-CNN), and TabNet. Experimental results show that both ML and DL approaches performed comparably. The RF model achieved the highest ML accuracy at 86.82%, while the 1D-CNN model attained a close 86.30%.

arXiv:2505.06280공식 코드 · Papers with Code

Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation

Prompt engineering has shown remarkable success with large language models, yet its systematic exploration in computer vision remains limited. In semantic segmentation, both textual and visual prompts offer distinct advantages: textual prompts through open-vocabulary methods allow segmentation of arbitrary categories, while visual reference prompts provide intuitive reference examples. However, existing benchmarks evaluate these modalities in isolation, without direct comparison under identical conditions. We present Show or Tell (SoT), a novel benchmark specifically designed to evaluate both visual and textual prompts for semantic segmentation across 14 datasets spanning 7 diverse domains (common scenes, urban, food, waste, parts, tools, and land-cover). We evaluate 5 open-vocabulary methods and 4 visual reference prompt approaches, adapting the latter to handle multi-class segmentation through a confidence-based mask merging strategy. Our extensive experiments reveal that open-vocabulary methods excel with common concepts easily described by text but struggle with complex domains like tools, while visual reference prompt methods achieve good average results but exhibit high variability depending on the input prompt. Through comprehensive quantitative and qualitative analysis, we identify the strengths and weaknesses of both prompting modalities, providing valuable insights to guide future research in vision foundation models for segmentation tasks.

arXiv:2504.17696공식 코드 · Papers with Code

Hierarchical and Multimodal Data for Daily Activity Understanding

Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in real-world settings. DARai consists of continuous scripted and unscripted recordings of 50 participants in 10 different environments, totaling over 200 hours of data from 20 sensors including multiple camera views, depth and radar sensors, wearable inertial measurement units (IMUs), electromyography (EMG), insole pressure sensors, biomonitor sensors, and gaze tracker. To capture the complexity in human activities, DARai is annotated at three levels of hierarchy: (i) high-level activities (L1) that are independent tasks, (ii) lower-level actions (L2) that are patterns shared between activities, and (iii) fine-grained procedures (L3) that detail the exact execution steps for actions. The dataset annotations and recordings are designed so that 22.7% of L2 actions are shared between L1 activities and 14.2% of L3 procedures are shared between L2 actions. The overlap and unscripted nature of DARai allows counterfactual activities in the dataset. Experiments with various machine learning models showcase the value of DARai in uncovering important challenges in human-centered applications. Specifically, we conduct unimodal and multimodal sensor fusion experiments for recognition, temporal localization, and future action anticipation across all hierarchical annotation levels. To highlight the limitations of individual sensors, we also conduct domain-variant experiments that are enabled by DARai's multi-sensor and counterfactual activity design setup. The code, documentation, and dataset are available at the dedicated DARai website: https://alregib.ece.gatech.edu/software-and-datasets/darai-daily-activity-recordings-for-artificial-intelligence-and-machine-learning/

arXiv:2504.04717공식 코드 · Papers with Code

Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models

Recent advancements in large language models (LLMs) have revolutionized their ability to handle single-turn tasks, yet real-world applications demand sophisticated multi-turn interactions. This survey provides a comprehensive review of recent advancements in evaluating and enhancing multi-turn interactions in LLMs. Focusing on task-specific scenarios, from instruction following in diverse domains such as math and coding to complex conversational engagements in roleplay, healthcare, education, and even adversarial jailbreak settings, we systematically examine the challenges of maintaining context, coherence, fairness, and responsiveness over prolonged dialogues. The paper organizes current benchmarks and datasets into coherent categories that reflect the evolving landscape of multi-turn dialogue evaluation. In addition, we review a range of enhancement methodologies under multi-turn settings, including model-centric strategies (contextual learning, supervised fine-tuning, reinforcement learning, and new architectures), external integration approaches (memory-augmented, retrieval-based methods, and knowledge graph), and agent-based techniques for collaborative interactions. Finally, we discuss open challenges and propose future directions for research to further advance the robustness and effectiveness of multi-turn interactions in LLMs. Related resources and papers are available at https://github.com/yubol-cmu/Awesome-Multi-Turn-LLMs.

arXiv:2503.12562공식 코드 · Papers with Code

History-Aware Transformation of ReID Features for Multiple Object Tracking

The aim of multiple object tracking (MOT) is to detect all objects in a video and bind them into multiple trajectories. Generally, this process is carried out in two steps: detecting objects and associating them across frames based on various cues and metrics. Many studies and applications adopt object appearance, also known as re-identification (ReID) features, for target matching through straightforward similarity calculation. However, we argue that this practice is overly naive and thus overlooks the unique characteristics of MOT tasks. Unlike regular re-identification tasks that strive to distinguish all potential targets in a general representation, multi-object tracking typically immerses itself in differentiating similar targets within the same video sequence. Therefore, we believe that seeking a more suitable feature representation space based on the different sample distributions of each sequence will enhance tracking performance. In this paper, we propose using history-aware transformations on ReID features to achieve more discriminative appearance representations. Specifically, we treat historical trajectory features as conditions and employ a tailored Fisher Linear Discriminant (FLD) to find a spatial projection matrix that maximizes the differentiation between different trajectories. Our extensive experiments reveal that this training-free projection can significantly boost feature-only trackers to achieve competitive, even superior tracking performance compared to state-of-the-art methods while also demonstrating impressive zero-shot transfer capabilities. This demonstrates the effectiveness of our proposal and further encourages future investigation into the importance and customization of ReID models in multiple object tracking. The code will be released at https://github.com/HELLORPG/HATReID-MOT.

arXiv:2502.04066공식 코드 · Papers with Code

SMI: An Information-Theoretic Metric for Predicting Model Knowledge Solely from Pre-Training Signals

The GPT-4 technical report highlights the possibility of predicting model performance on downstream tasks using only pre-training signals, though detailed methodologies are absent. Such predictive capabilities are essential for resource-efficient pre-training and the construction of task-aligned datasets. In this paper, we aim to predict performance in closed-book question answering (QA), a vital downstream task indicative of a model's internal knowledge. We address three primary challenges: (1) limited access to and understanding of pre-training corpora, (2) limitations of current evaluation methods for pre-trained models, and (3) limitations of frequency-based metrics in predicting model performance. In response to these challenges, we conduct large-scale retrieval and semantic analysis across the pre-training corpora of 21 publicly available and 3 custom-trained large language models. Subsequently, we develop a multi-template QA evaluation framework incorporating paraphrased question variants. Building on these foundations, we propose Size-dependent Mutual Information (SMI), an information-theoretic metric that linearly correlates pre-training data characteristics, model size, and QA accuracy, without requiring any additional training. The experimental results demonstrate that SMI outperforms co-occurrence-based baselines, achieving $R^2$ > 0.75 on models with over one billion parameters. Theoretical analysis further reveals the marginal benefits of scaling model size and optimizing data, indicating that the upper limit of specific QA task accuracy is approximately 80%. Our project is available at https://github.com/yuhui1038/SMI.

arXiv:2505.07705공식 코드 · Papers with Code

Codifying Character Logic in Role-Playing

This paper introduces Codified Profiles for role-playing, a novel approach that represents character logic as structured, executable functions for behavioral decision-making. Each profile defines a set of functions parse_by_scene(scene) that outputs a list of logic-grounded assertions triggered_statements, using both explicit control structures (e.g., if-then-else) and condition checks like check_condition(scene, question), where each question is a semantically meaningful prompt about the scene (e.g., "Is the character in danger?") discriminated by the role-playing LLM as true, false, or unknown. This explicit representation offers three key advantages over traditional prompt-based profiles, which append character descriptions directly into text prompts: (1) Persistence, by enforcing complete and consistent execution of character logic, rather than relying on the model's implicit reasoning; (2) Updatability, through systematic inspection and revision of behavioral logic, which is difficult to track or debug in prompt-only approaches; (3) Controllable Randomness, by supporting stochastic behavior directly within the logic, enabling fine-grained variability that prompting alone struggles to achieve. To validate these advantages, we introduce a new benchmark constructed from 83 characters and 5,141 scenes curated from Fandom, using NLI-based scoring to compare character responses against ground-truth actions. Our experiments demonstrate the significant benefits of codified profiles in improving persistence, updatability, and behavioral diversity. Notably, by offloading a significant portion of reasoning to preprocessing, codified profiles enable even 1B-parameter models to perform high-quality role-playing, providing a scalable and efficient foundation for local deployment of role-play agents.

arXiv:2505.07416공식 코드 · Papers with Code

ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation

Multimodal Review Helpfulness Prediction (MRHP) is an essential task in recommender systems, particularly in E-commerce platforms. Determining the helpfulness of user-generated reviews enhances user experience and improves consumer decision-making. However, existing datasets focus predominantly on English and Indonesian, resulting in a lack of linguistic diversity, especially for low-resource languages such as Vietnamese. In this paper, we introduce ViMRHP (Vietnamese Multimodal Review Helpfulness Prediction), a large-scale benchmark dataset for MRHP task in Vietnamese. This dataset covers four domains, including 2K products with 46K reviews. Meanwhile, a large-scale dataset requires considerable time and cost. To optimize the annotation process, we leverage AI to assist annotators in constructing the ViMRHP dataset. With AI assistance, annotation time is reduced (90 to 120 seconds per task down to 20 to 40 seconds per task) while maintaining data quality and lowering overall costs by approximately 65%. However, AI-generated annotations still have limitations in complex annotation tasks, which we further examine through a detailed performance analysis. In our experiment on ViMRHP, we evaluate baseline models on human-verified and AI-generated annotations to assess their quality differences. The ViMRHP dataset is publicly available at https://github.com/trng28/ViMRHP

arXiv:2505.07276공식 코드 · Papers with Code

FCPCA: Fuzzy clustering of high-dimensional time series based on common principal component analysis

Clustering multivariate time series data is a crucial task in many domains, as it enables the identification of meaningful patterns and groups in time-evolving data. Traditional approaches, such as crisp clustering, rely on the assumption that clusters are sufficiently separated with little overlap. However, real-world data often defy this assumption, exhibiting overlapping distributions or overlapping clouds of points and blurred boundaries between clusters. Fuzzy clustering offers a compelling alternative by allowing partial membership in multiple clusters, making it well-suited for these ambiguous scenarios. Despite its advantages, current fuzzy clustering methods primarily focus on univariate time series, and for multivariate cases, even datasets of moderate dimensionality become computationally prohibitive. This challenge is further exacerbated when dealing with time series of varying lengths, leaving a clear gap in addressing the complexities of modern datasets. This work introduces a novel fuzzy clustering approach based on common principal component analysis to address the aforementioned shortcomings. Our method has the advantage of efficiently handling high-dimensional multivariate time series by reducing dimensionality while preserving critical temporal features. Extensive numerical results show that our proposed clustering method outperforms several existing approaches in the literature. An interesting application involving brain signals from different drivers recorded from a simulated driving experiment illustrates the potential of the approach.

arXiv:2505.07179공식 코드 · Papers with Code

Lagrange Oscillatory Neural Networks for Constraint Satisfaction and Optimization

Physics-inspired computing paradigms are receiving renewed attention to enhance efficiency in compute-intensive tasks such as artificial intelligence and optimization. Similar to Hopfield neural networks, oscillatory neural networks (ONNs) minimize an Ising energy function that embeds the solutions of hard combinatorial optimization problems. Despite their success in solving unconstrained optimization problems, Ising machines still face challenges with constrained problems as they can get stuck at infeasible local minima. In this paper, we introduce a Lagrange ONN (LagONN) designed to escape infeasible states based on the theory of Lagrange multipliers. Unlike existing oscillatory Ising machines, LagONN employs additional Lagrange oscillators to guide the system towards feasible states in an augmented energy landscape and settles only when constraints are met. Taking the maximum satisfiability problem with three literals as a use case (Max-3-SAT), we harness LagONN's constraint satisfaction mechanism to find optimal solutions for random SATlib instances with up to 200 variables and 860 clauses, which provides a deterministic alternative to simulated annealing for coupled oscillators. We further discuss the potential of Lagrange oscillators to address other constraints, such as phase copying, which is useful in oscillatory Ising machines with limited connectivity.

arXiv:2505.07166공식 코드 · Papers with Code

Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition

Dense retrievers utilize pre-trained backbone language models (e.g., BERT, LLaMA) that are fine-tuned via contrastive learning to perform the task of encoding text into sense representations that can be then compared via a shallow similarity operation, e.g. inner product. Recent research has questioned the role of fine-tuning vs. that of pre-training within dense retrievers, specifically arguing that retrieval knowledge is primarily gained during pre-training, meaning knowledge not acquired during pre-training cannot be sub-sequentially acquired via fine-tuning. We revisit this idea here as the claim was only studied in the context of a BERT-based encoder using DPR as representative dense retriever. We extend the previous analysis by testing other representation approaches (comparing the use of CLS tokens with that of mean pooling), backbone architectures (encoder-only BERT vs. decoder-only LLaMA), and additional datasets (MSMARCO in addition to Natural Questions). Our study confirms that in DPR tuning, pre-trained knowledge underpins retrieval performance, with fine-tuning primarily adjusting neuron activation rather than reorganizing knowledge. However, this pattern does not hold universally, such as in mean-pooled (Contriever) and decoder-based (LLaMA) models. We ensure full reproducibility and make our implementation publicly available at https://github.com/ielab/DenseRetriever-Knowledge-Acquisition.

arXiv:2505.07161공식 코드 · Papers with Code

Towards Actionable Pedagogical Feedback: A Multi-Perspective Analysis of Mathematics Teaching and Tutoring Dialogue

Effective feedback is essential for refining instructional practices in mathematics education, and researchers often turn to advanced natural language processing (NLP) models to analyze classroom dialogues from multiple perspectives. However, utterance-level discourse analysis encounters two primary challenges: (1) multifunctionality, where a single utterance may serve multiple purposes that a single tag cannot capture, and (2) the exclusion of many utterances from domain-specific discourse move classifications, leading to their omission in feedback. To address these challenges, we proposed a multi-perspective discourse analysis that integrates domain-specific talk moves with dialogue act (using the flattened multi-functional SWBD-MASL schema with 43 tags) and discourse relation (applying Segmented Discourse Representation Theory with 16 relations). Our top-down analysis framework enables a comprehensive understanding of utterances that contain talk moves, as well as utterances that do not contain talk moves. This is applied to two mathematics education datasets: TalkMoves (teaching) and SAGA22 (tutoring). Through distributional unigram analysis, sequential talk move analysis, and multi-view deep dive, we discovered meaningful discourse patterns, and revealed the vital role of utterances without talk moves, demonstrating that these utterances, far from being mere fillers, serve crucial functions in guiding, acknowledging, and structuring classroom discourse. These insights underscore the importance of incorporating discourse relations and dialogue acts into AI-assisted education systems to enhance feedback and create more responsive learning environments. Our framework may prove helpful for providing human educator feedback, but also aiding in the development of AI agents that can effectively emulate the roles of both educators and students.

arXiv:2505.06972공식 코드 · Papers with Code

Web Page Classification using LLMs for Crawling Support

A web crawler is a system designed to collect web pages, and efficient crawling of new pages requires appropriate algorithms. While website features such as XML sitemaps and the frequency of past page updates provide important clues for accessing new pages, their universal application across diverse conditions is challenging. In this study, we propose a method to efficiently collect new pages by classifying web pages into two types, "Index Pages" and "Content Pages," using a large language model (LLM), and leveraging the classification results to select index pages as starting points for accessing new pages. We construct a dataset with automatically annotated web page types and evaluate our approach from two perspectives: the page type classification performance and coverage of new pages. Experimental results demonstrate that the LLM-based method outperformed baseline methods in both evaluation metrics.