PyTorchKR Papers

최신 논문

총 2,097편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.19721

Unleashing the Potential of Beamspace Modulation in Near-Field MIMO: Opportunities and Challenges

The principal distinction in transitioning from far-field multiple-input multiple-output (MIMO) systems to near-field MIMO configurations lies in the notable augmentation of spatial degrees of freedom (DoF). This increase is not static;rather, it dynamically fluctuates in response to user mobility. A critical challenge emerges in effectively leveraging this significantly enhanced and continuously evolving spatial DoF, particularly when constrained by a limited and energy-intensive array of radio frequency (RF) chains. This article presents an exhaustive review of the current methodologies for exploring spatial DoF in MIMO systems, with a particular emphasis on the near-field context. Central to this review is the exploration of beamspace modulation, a technique that ingeniously capitalizes on the increased and dynamic spatial DoFs inherent in near-field MIMO systems. This strategic exploitation is demonstrated to yield significant enhancements in both spectral efficiency and system reliability. Furthermore, the article delves into a detailed analysis of the multifaceted challenges associated with implementing this technology. Through this comprehensive evaluation, the work provides crucial insights into ongoing efforts to navigate these challenges and suggests potential pathways for future research in this rapidly evolving field.

arXiv:2410.03004

Multi-Motor Cargo Navigation in Complex Cytoskeletal Networks

The kinesin superfamily of motor proteins is a major driver of anterograde transport of vesicles and organelles within eukaryotic cells via microtubules. Numerous studies have elucidated the step-size, velocities, forces, and navigation ability of kinesins both in reconstituted systems and in live cells. Outside of cells, the kinesin-based transport is physically regulated and can be controlled by obstacles or defects in the path, or the interaction between several motors on the same cargo. To explore the physical control parameters on kinesin-driven transport, we created complex microtubule networks in vitro to test how kinesin cargoes made from quantum dots with one to 10 kinesin motors attached are able to navigate the network. We find that many motors on the quantum dot significantly alter distance walked, time spent bound, the average speed, and the tortuosity of the cargo. We also find that the average mesh size of the microtubule network affects the end-to-end distance of the motion, the run time, average speed and tortuosity of cargoes. Thus, both motor number and network density are physical aspects that regulate where cargoes traverse in space and time.

arXiv:2410.06195공식 코드 · Papers with Code

Entering Real Social World! Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective

Social intelligence is built upon three foundational pillars: cognitive intelligence, situational intelligence, and behavioral intelligence. As large language models (LLMs) become increasingly integrated into our social lives, understanding, evaluating, and developing their social intelligence are becoming increasingly important. While multiple existing works have investigated the social intelligence of LLMs, (1) most focus on a specific aspect, and the social intelligence of LLMs has yet to be systematically organized and studied; (2) position LLMs as passive observers from a third-person perspective, such as in Theory of Mind (ToM) tests. Compared to the third-person perspective, ego-centric first-person perspective evaluation can align well with actual LLM-based Agent use scenarios. (3) a lack of comprehensive evaluation of behavioral intelligence, with specific emphasis on incorporating critical human-machine interaction scenarios. In light of this, we present EgoSocialArena, a novel framework grounded in the three pillars of social intelligence: cognitive, situational, and behavioral intelligence, aimed to systematically evaluate the social intelligence of LLMs from a first-person perspective. With EgoSocialArena, we have conducted a comprehensive evaluation of eight prominent foundation models, even the most advanced LLMs like o1-preview lag behind human performance by 11.0 points.

arXiv:2410.06019

Unveiling Transformer Perception by Exploring Input Manifolds

This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical theory which describes the internal layers of a Transformer architecture as sequential deformations of the input manifold. Using eigendecomposition of the pullback of the distance metric defined on the output space through the Jacobian of the model, we are able to reconstruct equivalence classes in the input space and navigate across them. We illustrate how this method can be used as a powerful tool for investigating how a Transformer sees the input space, facilitating local and task-agnostic explainability in Computer Vision and Natural Language Processing tasks.

arXiv:2410.03546

Multidimensional Human Activity Recognition With Large Language Model: A Conceptual Framework

In high-stake environments like emergency response or elder care, the integration of large language model (LLM), revolutionize risk assessment, resource allocation, and emergency responses in Human Activity Recognition (HAR) systems by leveraging data from various wearable sensors. We propose a conceptual framework that utilizes various wearable devices, each considered as a single dimension, to support a multidimensional learning approach within HAR systems. By integrating and processing data from these diverse sources, LLMs can process and translate complex sensor inputs into actionable insights. This integration mitigates the inherent uncertainties and complexities associated with them, and thus enhancing the responsiveness and effectiveness of emergency services. This paper sets the stage for exploring the transformative potential of LLMs within HAR systems in empowering emergency workers to navigate the unpredictable and risky environments they encounter in their critical roles.

arXiv:2410.04263공식 코드 · Papers with Code

DeFoG: Discrete Flow Matching for Graph Generation

Graph generation is fundamental in diverse scientific applications, due to its ability to reveal the underlying distribution of complex data, and eventually generate new, realistic data points. Despite the success of diffusion models in this domain, those face limitations in sampling efficiency and flexibility, stemming from the tight coupling between the training and sampling stages. To address this, we propose DeFoG, a novel framework using discrete flow matching for graph generation. DeFoG employs a flow-based approach that features an efficient linear interpolation noising process and a flexible denoising process based on a continuous-time Markov chain formulation. We leverage an expressive graph transformer and ensure desirable node permutation properties to respect graph symmetry. Crucially, our framework enables a disentangled design of the training and sampling stages, enabling more effective and efficient optimization of model performance. We navigate this design space by introducing several algorithmic improvements that boost the model performance, consistently surpassing existing diffusion models. We also theoretically demonstrate that, for general discrete data, discrete flow models can faithfully replicate the ground truth distribution - a result that naturally extends to graph data and reinforces DeFoG's foundations. Extensive experiments show that DeFoG achieves state-of-the-art results on synthetic and molecular datasets, improving both training and sampling efficiency over diffusion models, and excels in conditional generation on a digital pathology dataset.

arXiv:2410.04811공식 코드 · Papers with Code

Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration

The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e.g., low-quality images or a Gaussian distribution. In this paper, we reformulate the trajectory optimization of this kind of method, focusing on enhancing both reconstruction quality and efficiency. Initially, we navigate effective restoration paths through a reinforcement learning process, gradually steering potential trajectories toward the most precise options. Additionally, to mitigate the considerable computational burden associated with iterative sampling, we propose cost-aware trajectory distillation to streamline complex paths into several manageable steps with adaptable sizes. Moreover, we fine-tune a foundational diffusion model (FLUX) with 12B parameters by using our algorithms, producing a unified framework for handling 7 kinds of image restoration tasks. Extensive experiments showcase the significant superiority of the proposed method, achieving a maximum PSNR improvement of 2.1 dB over state-of-the-art methods, while also greatly enhancing visual perceptual quality. Project page: \url{https://zhu-zhiyu.github.io/FLUX-IR/}.

arXiv:2410.05182공식 코드 · Papers with Code

MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain

The visual detection and tracking of surface terrain is required for spacecraft to safely land on or navigate within close proximity to celestial objects. Current approaches rely on template matching with pre-gathered patch-based features, which are expensive to obtain and a limiting factor in perceptual capability. While recent literature has focused on in-situ detection methods to enhance navigation and operational autonomy, robust description is still needed. In this work, we explore metric learning as the lightweight feature description mechanism and find that current solutions fail to address inter-class similarity and multi-view observational geometry. We attribute this to the view-unaware attention mechanism and introduce Multi-view Attention Regularizations (MARs) to constrain the channel and spatial attention across multiple feature views, regularizing the what and where of attention focus. We thoroughly analyze many modern metric learning losses with and without MARs and demonstrate improved terrain-feature recognition performance by upwards of 85%. We additionally introduce the Luna-1 dataset, consisting of Moon crater landmarks and reference navigation frames from NASA mission data to support future research in this difficult task. Luna-1 and source code are publicly available at https://droneslab.github.io/mars/.

arXiv:2410.05243공식 코드 · Papers with Code

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms. However, the effectiveness of these agents hinges on the robustness of their grounding capability. Current GUI agents predominantly utilize text-based representations such as HTML or accessibility trees, which, despite their utility, often introduce noise, incompleteness, and increased computational overhead. In this paper, we advocate a human-like embodiment for GUI agents that perceive the environment entirely visually and directly take pixel-level operations on the GUI. The key is visual grounding models that can accurately map diverse referring expressions of GUI elements to their coordinates on the GUI across different platforms. We show that a simple recipe, which includes web-based synthetic data and slight adaptation of the LLaVA architecture, is surprisingly effective for training such visual grounding models. We collect the largest dataset for GUI visual grounding so far, containing 10M GUI elements and their referring expressions over 1.3M screenshots, and use it to train UGround, a strong universal visual grounding model for GUI agents. Empirical results on six benchmarks spanning three categories (grounding, offline agent, and online agent) show that 1) UGround substantially outperforms existing visual grounding models for GUI agents, by up to 20% absolute, and 2) agents with UGround outperform state-of-the-art agents, despite the fact that existing agents use additional text-based input while ours only uses visual perception. These results provide strong support for the feasibility and promises of GUI agents that navigate the digital world as humans do.

arXiv:2410.03560

færdXel: An Expert System for Danish Traffic Law

We present f{\ae}rdXel, a tool for symbolic reasoning in the domain of Danish traffic law. f{\ae}rdXel combines techniques from logic programming with a novel interface that allows users to navigate through its reasoning process, thereby ensuring the system's trustworthiness. A preliminary empirical evaluation indicates that this work is seen as very promising, and has the potential to become a foundation for real-world AI tools supporting professionals in the Danish legal sector.

arXiv:2410.03494공식 코드 · Papers with Code

Generative Artificial Intelligence for Navigating Synthesizable Chemical Space

We introduce SynFormer, a generative modeling framework designed to efficiently explore and navigate synthesizable chemical space. Unlike traditional molecular generation approaches, we generate synthetic pathways for molecules to ensure that designs are synthetically tractable. By incorporating a scalable transformer architecture and a diffusion module for building block selection, SynFormer surpasses existing models in synthesizable molecular design. We demonstrate SynFormer's effectiveness in two key applications: (1) local chemical space exploration, where the model generates synthesizable analogs of a reference molecule, and (2) global chemical space exploration, where the model aims to identify optimal molecules according to a black-box property prediction oracle. Additionally, we demonstrate the scalability of our approach via the improvement in performance as more computational resources become available. With our code and trained models openly available, we hope that SynFormer will find use across applications in drug discovery and materials science.

arXiv:2409.20242

Design and validation of a fuzzy logic controller for multi-section continuum robots

The rise of multi-section continuum robots (CRs) has captivated researchers and practitioners across diverse industries and medical fields. Accurate modeling of these dexterous manipulators continues to be a significant challenge. This complexity stems primarily from many nonlinearities that plague their behavior, including hysteresis and cable elongation. Researchers have devised a spectrum of model-based and learning-based strategies to navigate this intricate landscape, aiming to conquer the modeling problem and elevate control performance. Despite the advancements in these approaches, they encounter challenges stemming from their complex design and intricate learning processes, impairing versatility and hindering robust closed-loop control. This paper introduces a simple-structured, model-less fuzzy logic controller for the closed-loop control of continuum robots. Unlike traditional methods relying on complex models and numerous sensors, this controller boasts a built-in shape reconstruction algorithm. This algorithm allows it to achieve robust control using only the feedback of end position and orientation, significantly reducing sensor dependence. It efficiently adapts to various nonlinearities like hysteresis, cable elongation, and unexpected external disturbances. The experimental results conclusively demonstrate the accuracy and robustness of the proposed fuzzy controller. On a three-section, six-degree-of-freedom continuum robot, it achieved a miniscule trajectory tracking Root Mean Square Error (RMSE) from 0.28 to 0.54 mm, representing just 0.17 to 0.32% of the robot's length. Additionally, the controller demonstrates robustness by successfully handling an unexpected external disturbance of 100g during the trajectory tracking.

arXiv:2409.15323

Introducing ELLIPS: An Ethics-Centered Approach to Research on LLM-Based Inference of Psychiatric Conditions

As mental health care systems worldwide struggle to meet demand, there is increasing focus on using language models to infer neuropsychiatric conditions or psychopathological traits from language production. Yet, so far, this research has only delivered solutions with limited clinical applicability, due to insufficient consideration of ethical questions crucial to ensuring the synergy between possible applications and model design. To accelerate progress towards clinically applicable models, our paper charts the ethical landscape of research on language-based inference of psychopathology and provides a practical tool for researchers to navigate it. We identify seven core ethical principles that should guide model development and deployment in this domain, translate them into ELLIPS, an ethical toolkit operationalizing these principles into questions that can guide researchers' choices with respect to data selection, architectures, evaluation, and model deployment, and provide a case study exemplifying its use. With this, we aim to facilitate the emergence of model technology with concrete potential for real-world applicability.

arXiv:2410.01428

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and retrieval-augmented generation (RAG) to decompose a complex problem into simpler steps and apply retrieval to improve factual correctness. These methods work well on straightforward reasoning tasks but often falter on challenging tasks such as competitive programming and mathematics, due to frequent reasoning errors and irrelevant knowledge retrieval. To address this, we introduce Critic-guided planning with Retrieval-augmentation, CR-Planner, a novel framework that leverages fine-tuned critic models to guide both reasoning and retrieval processes through planning. CR-Planner solves a problem by iteratively selecting and executing sub-goals. Initially, it identifies the most promising sub-goal from reasoning, query generation, and retrieval, guided by rewards given by a critic model named sub-goal critic. It then executes this sub-goal through sampling and selecting the optimal output based on evaluations from another critic model named execution critic. This iterative process, informed by retrieved information and critic models, enables CR-Planner to effectively navigate the solution space towards the final answer. We employ Monte Carlo Tree Search to collect the data for training the critic models, allowing for a systematic exploration of action sequences and their long-term impacts. We validate CR-Planner on challenging domain-knowledge-intensive and reasoning-heavy tasks, including competitive programming, theorem-driven math reasoning, and complex domain retrieval problems. Our experiments demonstrate that CR-Planner significantly outperforms baselines, highlighting its effectiveness in addressing challenging problems by improving both reasoning and retrieval.

arXiv:2410.00408

ECORS: An Ensembled Clustering Approach to Eradicate The Local And Global Outlier In Collaborative Filtering Recommender System

Recommender systems are designed to suggest items based on user preferences, helping users navigate the vast amount of information available on the internet. Given the overwhelming content, outlier detection has emerged as a key research area in recommender systems. It involves identifying unusual or suspicious patterns in user behavior. However, existing studies in this field face several challenges, including the limited universality of algorithms, difficulties in selecting users, and a lack of optimization. In this paper, we propose an approach that addresses these challenges by employing various clustering algorithms. Specifically, we utilize a user-user matrix-based clustering technique to detect outliers. By constructing a user-user matrix, we can identify suspicious users in the system. Both local and global outliers are detected to ensure comprehensive analysis. Our experimental results demonstrate that this approach significantly improves the accuracy of outlier detection in recommender systems.

arXiv:2410.01088공식 코드 · Papers with Code

Exploring Empty Spaces: Human-in-the-Loop Data Augmentation

Data augmentation is crucial to make machine learning models more robust and safe. However, augmenting data can be challenging as it requires generating diverse data points to rigorously evaluate model behavior on edge cases and mitigate potential harms. Creating high-quality augmentations that cover these "unknown unknowns" is a time- and creativity-intensive task. In this work, we introduce Amplio, an interactive tool to help practitioners navigate "unknown unknowns" in unstructured text datasets and improve data diversity by systematically identifying empty data spaces to explore. Amplio includes three human-in-the-loop data augmentation techniques: Augment With Concepts, Augment by Interpolation, and Augment with Large Language Model. In a user study with 18 professional red teamers, we demonstrate the utility of our augmentation methods in helping generate high-quality, diverse, and relevant model safety prompts. We find that Amplio enabled red teamers to augment data quickly and creatively, highlighting the transformative potential of interactive augmentation workflows.

arXiv:2410.00386

Seamless Augmented Reality Integration in Arthroscopy: A Pipeline for Articular Reconstruction and Guidance

Arthroscopy is a minimally invasive surgical procedure used to diagnose and treat joint problems. The clinical workflow of arthroscopy typically involves inserting an arthroscope into the joint through a small incision, during which surgeons navigate and operate largely by relying on their visual assessment through the arthroscope. However, the arthroscope's restricted field of view and lack of depth perception pose challenges in navigating complex articular structures and achieving surgical precision during procedures. Aiming at enhancing intraoperative awareness, we present a robust pipeline that incorporates simultaneous localization and mapping, depth estimation, and 3D Gaussian splatting to realistically reconstruct intra-articular structures solely based on monocular arthroscope video. Extending 3D reconstruction to Augmented Reality (AR) applications, our solution offers AR assistance for articular notch measurement and annotation anchoring in a human-in-the-loop manner. Compared to traditional Structure-from-Motion and Neural Radiance Field-based methods, our pipeline achieves dense 3D reconstruction and competitive rendering fidelity with explicit 3D representation in 7 minutes on average. When evaluated on four phantom datasets, our method achieves RMSE = 2.21mm reconstruction error, PSNR = 32.86 and SSIM = 0.89 on average. Because our pipeline enables AR reconstruction and guidance directly from monocular arthroscopy without any additional data and/or hardware, our solution may hold the potential for enhancing intraoperative awareness and facilitating surgical precision in arthroscopy. Our AR measurement tool achieves accuracy within 1.59 +/- 1.81mm and the AR annotation tool achieves a mIoU of 0.721.

arXiv:2410.01273

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

Real-life robot navigation involves more than just reaching a destination; it requires optimizing movements while addressing scenario-specific goals. An intuitive way for humans to express these goals is through abstract cues like verbal commands or rough sketches. Such human guidance may lack details or be noisy. Nonetheless, we expect robots to navigate as intended. For robots to interpret and execute these abstract instructions in line with human expectations, they must share a common understanding of basic navigation concepts with humans. To this end, we introduce CANVAS, a novel framework that combines visual and linguistic instructions for commonsense-aware navigation. Its success is driven by imitation learning, enabling the robot to learn from human navigation behavior. We present COMMAND, a comprehensive dataset with human-annotated navigation results, spanning over 48 hours and 219 km, designed to train commonsense-aware navigation systems in simulated environments. Our experiments show that CANVAS outperforms the strong rule-based system ROS NavStack across all environments, demonstrating superior performance with noisy instructions. Notably, in the orchard environment, where ROS NavStack records a 0% total success rate, CANVAS achieves a total success rate of 67%. CANVAS also closely aligns with human demonstrations and commonsense constraints, even in unseen environments. Furthermore, real-world deployment of CANVAS showcases impressive Sim2Real transfer with a total success rate of 69%, highlighting the potential of learning from human demonstrations in simulated environments for real-world applications.

arXiv:2410.01782공식 코드 · Papers with Code

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence, particularly when using open-source LLMs. To mitigate this gap, we introduce a novel framework, Open-RAG, designed to enhance reasoning capabilities in RAG with open-source LLMs. Our framework transforms an arbitrary dense LLM into a parameter-efficient sparse mixture of experts (MoE) model capable of handling complex reasoning tasks, including both single- and multi-hop queries. Open-RAG uniquely trains the model to navigate challenging distractors that appear relevant but are misleading. As a result, Open-RAG leverages latent learning, dynamically selecting relevant experts and integrating external knowledge effectively for more accurate and contextually relevant responses. In addition, we propose a hybrid adaptive retrieval method to determine retrieval necessity and balance the trade-off between performance gain and inference speed. Experimental results show that the Llama2-7B-based Open-RAG outperforms state-of-the-art LLMs and RAG models such as ChatGPT, Self-RAG, and Command R+ in various knowledge-intensive tasks. We open-source our code and models at https://openragmoe.github.io/

arXiv:2409.19459

Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments

In this paper, we develop an embodied AI system for human-in-the-loop navigation with a wheeled mobile robot. We propose a direct yet effective method of monitoring the robot's current plan to detect changes in the environment that impact the intended trajectory of the robot significantly and then query a human for feedback. We also develop a means to parse human feedback expressed in natural language into local navigation waypoints and integrate it into a global planning system, by leveraging a map of semantic features and an aligned obstacle map. Extensive testing in simulation and physical hardware experiments with a resource-constrained wheeled robot tasked to navigate in a real-world environment validate the efficacy and robustness of our method. This work can support applications like precision agriculture and construction, where persistent monitoring of the environment provides a human with information about the environment state.