PyTorchKR Papers

최신 논문

총 1,904편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2504.21432

UAV-VLN: End-to-End Vision Language guided Navigation for UAVs

A core challenge in AI-guided autonomy is enabling agents to navigate realistically and effectively in previously unseen environments based on natural language commands. We propose UAV-VLN, a novel end-to-end Vision-Language Navigation (VLN) framework for Unmanned Aerial Vehicles (UAVs) that seamlessly integrates Large Language Models (LLMs) with visual perception to facilitate human-interactive navigation. Our system interprets free-form natural language instructions, grounds them into visual observations, and plans feasible aerial trajectories in diverse environments. UAV-VLN leverages the common-sense reasoning capabilities of LLMs to parse high-level semantic goals, while a vision model detects and localizes semantically relevant objects in the environment. By fusing these modalities, the UAV can reason about spatial relationships, disambiguate references in human instructions, and plan context-aware behaviors with minimal task-specific supervision. To ensure robust and interpretable decision-making, the framework includes a cross-modal grounding mechanism that aligns linguistic intent with visual context. We evaluate UAV-VLN across diverse indoor and outdoor navigation scenarios, demonstrating its ability to generalize to novel instructions and environments with minimal task-specific training. Our results show significant improvements in instruction-following accuracy and trajectory efficiency, highlighting the potential of LLM-driven vision-language interfaces for safe, intuitive, and generalizable UAV autonomy.

arXiv:2505.00831공식 코드 · Papers with Code

SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation

Efficient path planning in robotics, particularly within large-scale, dynamic environments, remains a significant hurdle. While Large Language Models (LLMs) offer strong reasoning capabilities, their high computational cost and limited adaptability in dynamic scenarios hinder real-time deployment on edge devices. We present SmallPlan -- a novel framework leveraging LLMs as teacher models to train lightweight Small Language Models (SLMs) for high-level path planning tasks. In SmallPlan, the SLMs provide optimal action sequences to navigate across scene graphs that compactly represent full-scaled 3D scenes. The SLMs are trained in a simulation-powered, interleaved manner with LLM-guided supervised fine-tuning (SFT) and reinforcement learning (RL). This strategy not only enables SLMs to successfully complete navigation tasks but also makes them aware of important factors like travel distance and number of trials. Through experiments, we demonstrate that the fine-tuned SLMs perform competitively with larger models like GPT-4o on sequential path planning, without suffering from hallucination and overfitting. SmallPlan is resource-efficient, making it well-suited for edge-device deployment and advancing practical autonomous robotics. Our source code is available here: https://github.com/quangpham2006/SmallPlan

arXiv:2504.17331

Exploring Context-aware and LLM-driven Locomotion for Immersive Virtual Reality

Locomotion plays a crucial role in shaping the user experience within virtual reality environments. In particular, hands-free locomotion offers a valuable alternative by supporting accessibility and freeing users from reliance on handheld controllers. To this end, traditional speech-based methods often depend on rigid command sets, limiting the naturalness and flexibility of interaction. In this study, we propose a novel locomotion technique powered by large language models (LLMs), which allows users to navigate virtual environments using natural language with contextual awareness. We evaluate three locomotion methods: controller-based teleportation, voice-based steering, and our language model-driven approach. Our evaluation measures include eye-tracking data analysis, including explainable machine learning through SHAP analysis as well as standardized questionnaires for usability, presence, cybersickness, and cognitive load to examine user attention and engagement. Our findings indicate that the LLM-driven locomotion possesses comparable usability, presence, and cybersickness scores to established methods like teleportation, demonstrating its novel potential as a comfortable, natural language-based, hands-free alternative. In addition, it enhances user attention within the virtual environment, suggesting greater engagement. Complementary to these findings, SHAP analysis revealed that fixation, saccade, and pupil-related features vary across techniques, indicating distinct patterns of visual attention and cognitive processing. Overall, we state that our method can facilitate hands-free locomotion in virtual spaces, especially in supporting accessibility.

arXiv:2504.16062공식 코드 · Papers with Code

ForesightNav: Learning Scene Imagination for Efficient Exploration

Understanding how humans leverage prior knowledge to navigate unseen environments while making exploratory decisions is essential for developing autonomous robots with similar abilities. In this work, we propose ForesightNav, a novel exploration strategy inspired by human imagination and reasoning. Our approach equips robotic agents with the capability to predict contextual information, such as occupancy and semantic details, for unexplored regions. These predictions enable the robot to efficiently select meaningful long-term navigation goals, significantly enhancing exploration in unseen environments. We validate our imagination-based approach using the Structured3D dataset, demonstrating accurate occupancy prediction and superior performance in anticipating unseen scene geometry. Our experiments show that the imagination module improves exploration efficiency in unseen environments, achieving a 100% completion rate for PointNav and an SPL of 67% for ObjectNav on the Structured3D Validation split. These contributions demonstrate the power of imagination-driven reasoning for autonomous systems to enhance generalizable and efficient exploration.

arXiv:2504.20628

Cognitive maps are generative programs

Making sense of the world and acting in it relies on building simplified mental representations that abstract away aspects of reality. This principle of cognitive mapping is universal to agents with limited resources. Living organisms, people, and algorithms all face the problem of forming functional representations of their world under various computing constraints. In this work, we explore the hypothesis that human resource-efficient planning may arise from representing the world as predictably structured. Building on the metaphor of concepts as programs, we propose that cognitive maps can take the form of generative programs that exploit predictability and redundancy, in contrast to directly encoding spatial layouts. We use a behavioral experiment to show that people who navigate in structured spaces rely on modular planning strategies that align with programmatic map representations. We describe a computational model that predicts human behavior in a variety of structured scenarios. This model infers a small distribution over possible programmatic cognitive maps conditioned on human prior knowledge of the world, and uses this distribution to generate resource-efficient plans. Our models leverages a Large Language Model as an embedding of human priors, implicitly learned through training on a vast corpus of human data. Our model demonstrates improved computational efficiency, requires drastically less memory, and outperforms unstructured planning algorithms with cognitive constraints at predicting human behavior, suggesting that human planning strategies rely on programmatic cognitive maps.

arXiv:2504.17534

Learning Isometric Embeddings of Road Networks using Multidimensional Scaling

The lack of generalization in learning-based autonomous driving applications is shown by the narrow range of road scenarios that vehicles can currently cover. A generalizable approach should capture many distinct road structures and topologies, as well as consider traffic participants, and dynamic changes in the environment, so that vehicles can navigate and perform motion planning tasks even in the most difficult situations. Designing suitable feature spaces for neural network-based motion planers that encapsulate all kinds of road scenarios is still an open research challenge. This paper tackles this learning-based generalization challenge and shows how graph representations of road networks can be leveraged by using multidimensional scaling (MDS) techniques in order to obtain such feature spaces. State-of-the-art graph representations and MDS approaches are analyzed for the autonomous driving use case. Finally, the option of embedding graph nodes is discussed in order to perform easier learning procedures and obtain dimensionality reduction.

arXiv:2504.18601

The Philosophic Turn for AI Agents: Replacing centralized digital rhetoric with decentralized truth-seeking

In the face of rapidly advancing AI technology, individuals will increasingly rely on AI agents to navigate life's growing complexities, raising critical concerns about maintaining both human agency and autonomy. This paper addresses a fundamental dilemma posed by AI decision-support systems: the risk of either becoming overwhelmed by complex decisions, thus losing agency, or having autonomy compromised by externally controlled choice architectures reminiscent of ``nudging'' practices. While the ``nudge'' framework, based on the use of choice-framing to guide individuals toward presumed beneficial outcomes, initially appeared to preserve liberty, at AI-driven scale, it threatens to erode autonomy. To counteract this risk, the paper proposes a philosophic turn in AI design. AI should be constructed to facilitate decentralized truth-seeking and open-ended inquiry, mirroring the Socratic method of philosophical dialogue. By promoting individual and collective adaptive learning, such AI systems would empower users to maintain control over their judgments, augmenting their agency without undermining autonomy. The paper concludes by outlining essential features for autonomy-preserving AI systems, sketching a path toward AI systems that enhance human judgment rather than undermine it.

arXiv:2505.01754

Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias

Biased news reporting poses a significant threat to informed decision-making and the functioning of democracies. This study introduces a novel methodology for scalable, minimally biased analysis of media bias in political news. The proposed approach examines event selection, labeling, word choice, and commission and omission biases across news sources by leveraging natural language processing techniques, including hierarchical topic modeling, sentiment analysis, and ontology learning with large language models. Through three case studies related to current political events, we demonstrate the methodology's effectiveness in identifying biases across news sources at various levels of granularity. This work represents a significant step towards scalable, minimally biased media bias analysis, laying the groundwork for tools to help news consumers navigate an increasingly complex media landscape.

arXiv:2505.02306

SafeMate: A Modular RAG-Based Agent for Context-Aware Emergency Guidance

Despite the abundance of public safety documents and emergency protocols, most individuals remain ill-equipped to interpret and act on such information during crises. Traditional emergency decision support systems (EDSS) are designed for professionals and rely heavily on static documents like PDFs or SOPs, which are difficult for non-experts to navigate under stress. This gap between institutional knowledge and public accessibility poses a critical barrier to effective emergency preparedness and response. We introduce SafeMate, a retrieval-augmented AI assistant that delivers accurate, context-aware guidance to general users in both preparedness and active emergency scenarios. Built on the Model Context Protocol (MCP), SafeMate dynamically routes user queries to tools for document retrieval, checklist generation, and structured summarization. It uses FAISS with cosine similarity to identify relevant content from trusted sources.

arXiv:2505.02272

Robust Localization, Mapping, and Navigation for Quadruped Robots

Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a robust localization, mapping, and navigation system for low-cost quadruped robots. In pursuit of this objective we combine contact-aided kinematic, visual-inertial odometry, and depth-stabilized vision, enhancing stability and accuracy of the system. Our results in simulation and two different real-world quadruped platforms show that our system can generate an accurate 2D map of the environment, robustly localize itself, and navigate autonomously. Furthermore, we present in-depth ablation studies of the important components of the system and their impact on localization accuracy. Videos, code, and additional experiments can be found on the project website: https://sites.google.com/view/low-cost-quadruped-slam

논문 ID: 6982.05447

ONLINE FOOD ORDERING SYSTEM PROJECT REPORT

Online Food Ordering System is proposed for simplifies the food ordering process. This System shows an user interface and update the menu with all available options so that it eases the customer work. Customer can choose more than one item to make an order and can view Order details before logging off. The order confirmation is sent to the customer. The order is placed in the queue and updated in the Database and returned in real time. This system assists the staff to go through the orders in real time and process it efficiently. Online food order system is mainly designed primarily function for use in the food delivery industry. This system will allow hotels and restaurants to increase online food ordering such type of business. The customers can be selected food menu items just few minutes. In the modern food industries allows to quickly and easily delivery on customer place. Restaurant employees then use these orders through an easy to delivery on customer place easy find out navigate graphical interface for efficient processing.

논문 ID: 1519.62885

TEACHERS RECORD MANAGEMENT SYSTEM PROJECT REPORT.

The Teachers Record Management System is a comprehensive solution designed to simplify the process of managing teacher records. In today's fast-paced world, it is imperative for schools and individuals to have access to accurate and up-to-date information about teachers. This system addresses the needs of both individuals and schools, offering an efficient and effective way to manage teacher records. This web-based technology was developed with the aim of providing an easy-to-use platform that allows users to search and manage teacher records with ease. The system is designed to be user-friendly, making it accessible to individuals with varying levels of computer literacy. The interface is intuitive and easy to navigate, making it possible for users to quickly find the information they need. For individuals who are searching for good teachers, the Teachers Record Management System offers a comprehensive database of teacher records that can be searched using various parameters such as subject, qualification, experience, and location. This allows users to find the best teachers that match their requirements in a matter of minutes. The system also offers the ability to rate and review teachers, providing valuable feedback to other users who are looking for good teachers. For schools, the Teachers Record Management System offers a robust and secure platform for managing teacher records. The system allows schools to maintain accurate and up-to-date records of their teachers, including their personal information, academic qualifications, work experience, and other relevant details. This makes it easy for schools to keep track of their teachers and ensure that they have the right teachers for the job. The system also offers a range of features that help schools manage their teachers more efficiently. For example, the system allows schools to schedule classes and assign teachers to specific classes based on their qualifications and experience. It also offers a range of reporting and analytics tools that enable schools to track their teacher's performance and identify areas where improvements can be made. In conclusion, the Teachers Record Management System is a powerful tool that offers a range of benefits to both individuals and schools. It provides an easy and efficient way to search and manage teacher records, allowing users to find the best teachers that match their requirements. The system is also designed to be user-friendly and offers a range of features that help schools manage their teachers more efficiently. Overall, the Teachers Record Management System is an essential tool for anyone who wants to find good teachers or manage their teacher records.

논문 ID: 0597.59360

A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT

Online movie ticket booking system for movies is a web-based program. This application allows users to purchase cinema tickets over the portal. To buy tickets, people must first register or log in. This website's backend is PHP and JavaScript, and the front end is HTML and CSS. All phases of the software development life cycle are efficiently managed in order to design and implement software. On the website, there are two panels: one for administrators and one for customers/users. The admin has the ability to add cinemas, movies, delete, halt execution, and add screens, among other things. The website is simple to navigate and appealing, saving the end user time.

arXiv:2504.14985

aiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models (LLMs) for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation platform for LLM safety and security. aiXamine integrates over 40 tests (i.e., benchmarks) organized into eight key services targeting specific dimensions of safety and security: adversarial robustness, code security, fairness and bias, hallucination, model and data privacy, out-of-distribution (OOD) robustness, over-refusal, and safety alignment. The platform aggregates the evaluation results into a single detailed report per model, providing a detailed breakdown of model performance, test examples, and rich visualizations. We used aiXamine to assess over 50 publicly available and proprietary LLMs, conducting over 2K examinations. Our findings reveal notable vulnerabilities in leading models, including susceptibility to adversarial attacks in OpenAI's GPT-4o, biased outputs in xAI's Grok-3, and privacy weaknesses in Google's Gemini 2.0. Additionally, we observe that open-source models can match or exceed proprietary models in specific services such as safety alignment, fairness and bias, and OOD robustness. Finally, we identify trade-offs between distillation strategies, model size, training methods, and architectural choices.

arXiv:2504.12982

Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Reliable Response Generation in the Wild

The proliferation of large language models (LLMs) has significantly advanced information retrieval systems, particularly in response generation (RG). Unfortunately, LLMs often face knowledge conflicts between internal memory and retrievaled external information, arising from misinformation, biases, or outdated knowledge. These conflicts undermine response reliability and introduce uncertainty in decision-making. In this work, we analyze how LLMs navigate knowledge conflicts from an information-theoretic perspective and reveal that when conflicting and supplementary information exhibit significant differences, LLMs confidently resolve their preferences. However, when the distinction is ambiguous, LLMs experience heightened uncertainty. Based on this insight, we propose Swin-VIB, a novel framework that integrates a pipeline of variational information bottleneck models into adaptive augmentation of retrieved information and guiding LLM preference in response generation. Extensive experiments on single-choice, open-ended question-answering (QA), and retrieval augmented generation (RAG) validate our theoretical findings and demonstrate the efficacy of Swin-VIB. Notably, our method improves single-choice task accuracy by at least 7.54\% over competitive baselines.

arXiv:2504.12682

WebLists: Extracting Structured Information From Complex Interactive Websites Using Executable LLM Agents

Most recent web agent research has focused on navigation and transaction tasks, with little emphasis on extracting structured data at scale. We present WebLists, a benchmark of 200 data-extraction tasks across four common business and enterprise use-cases. Each task requires an agent to navigate to a webpage, configure it appropriately, and extract complete datasets with well-defined schemas. We show that both LLMs with search capabilities and SOTA web agents struggle with these tasks, with a recall of 3% and 31%, respectively, despite higher performance on question-answering tasks. To address this challenge, we propose BardeenAgent, a novel framework that enables web agents to convert their execution into repeatable programs, and replay them at scale across pages with similar structure. BardeenAgent is also the first LLM agent to take advantage of the regular structure of HTML. In particular BardeenAgent constructs a generalizable CSS selector to capture all relevant items on the page, then fits the operations to extract the data. On the WebLists benchmark, BardeenAgent achieves 66% recall overall, more than doubling the performance of SOTA web agents, and reducing cost per output row by 3x.

arXiv:2504.12654

The Paradox of Professional Input: How Expert Collaboration with AI Systems Shapes Their Future Value

This perspective paper examines a fundamental paradox in the relationship between professional expertise and artificial intelligence: as domain experts increasingly collaborate with AI systems by externalizing their implicit knowledge, they potentially accelerate the automation of their own expertise. Through analysis of multiple professional contexts, we identify emerging patterns in human-AI collaboration and propose frameworks for professionals to navigate this evolving landscape. Drawing on research in knowledge management, expertise studies, human-computer interaction, and labor economics, we develop a nuanced understanding of how professional value may be preserved and transformed in an era of increasingly capable AI systems. Our analysis suggests that while the externalization of tacit knowledge presents certain risks to traditional professional roles, it also creates opportunities for the evolution of expertise and the emergence of new forms of professional value. We conclude with implications for professional education, organizational design, and policy development that can help ensure the codification of expert knowledge enhances rather than diminishes the value of human expertise.

arXiv:2504.12075

Generative Deep Learning Framework for Inverse Design of Fuels

In the present work, a generative deep learning framework combining a Co-optimized Variational Autoencoder (Co-VAE) architecture with quantitative structure-property relationship (QSPR) techniques is developed to enable accelerated inverse design of fuels. The Co-VAE integrates a property prediction component coupled with the VAE latent space, enhancing molecular reconstruction and accurate estimation of Research Octane Number (RON) (chosen as the fuel property of interest). A subset of the GDB-13 database, enriched with a curated RON database, is used for model training. Hyperparameter tuning is further utilized to optimize the balance among reconstruction fidelity, chemical validity, and RON prediction. An independent regression model is then used to refine RON prediction, while a differential evolution algorithm is employed to efficiently navigate the VAE latent space and identify promising fuel molecule candidates with high RON. This methodology addresses the limitations of traditional fuel screening approaches by capturing complex structure-property relationships within a comprehensive latent representation. The generative model provides a flexible tool for systematically exploring vast chemical spaces, paving the way for discovering fuels with superior anti-knock properties. The demonstrated approach can be readily extended to incorporate additional fuel properties and synthesizability criteria to enhance applicability and reliability for de novo design of new fuels.

arXiv:2504.10499

Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey

Large language models (LLMs) struggle with the factual error during inference due to the lack of sufficient training data and the most updated knowledge, leading to the hallucination problem. Retrieval-Augmented Generation (RAG) has gained attention as a promising solution to address the limitation of LLMs, by retrieving relevant information from external source to generate more accurate answers to the questions. Given the pervasive presence of structured knowledge in the external source, considerable strides in RAG have been made to employ the techniques related to graphs and achieve more complex reasoning based on the topological information between knowledge entities. However, there is currently neither unified review examining the diverse roles of graphs in RAG, nor a comprehensive resource to help researchers navigate and contribute to this evolving field. This survey offers a novel perspective on the functionality of graphs within RAG and their impact on enhancing performance across a wide range of graph-structured data. It provides a detailed breakdown of the roles that graphs play in RAG, covering database construction, algorithms, pipelines, and tasks. Finally, it identifies current challenges and outline future research directions, aiming to inspire further developments in this field. Our graph-centered analysis highlights the commonalities and differences in existing methods, setting the stage for future researchers in areas such as graph learning, database systems, and natural language processing.

arXiv:2504.10724

HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving

Deploying large language models (LLMs) presents critical challenges due to the inherent trade-offs associated with key performance metrics, such as latency, accuracy, and throughput. Typically, gains in one metric is accompanied with degradation in others. Early-Exit LLMs (EE-LLMs) efficiently navigate this trade-off space by skipping some of the later model layers when it confidently finds an output token early, thus reducing latency without impacting accuracy. However, as the early exits taken depend on the task and are unknown apriori to request processing, EE-LLMs conservatively load the entire model, limiting resource savings and throughput. Also, current frameworks statically select a model for a user task, limiting our ability to adapt to changing nature of the input queries. We propose HELIOS to address these challenges. First, HELIOS shortlists a set of candidate LLMs, evaluates them using a subset of prompts, gathering telemetry data in real-time. Second, HELIOS uses the early exit data from these evaluations to greedily load the selected model only up to a limited number of layers. This approach yields memory savings which enables us to process more requests at the same time, thereby improving throughput. Third, HELIOS monitors and periodically reassesses the performance of the candidate LLMs and if needed, switches to another model that can service incoming queries more efficiently (such as using fewer layers without lowering accuracy). Our evaluations show that HELIOS achieves 1.48$\times$ throughput, 1.10$\times$ energy-efficiency, 1.39$\times$ lower response time, and 3.7$\times$ improvements in inference batch sizes compared to the baseline, when optimizing for the respective service level objectives.