搜索结果：guide

There are substantial instructional videos on the Internet, which provide us tutorials for completing various tasks. Existing instructional video datasets only focus on specific steps at the video level, lacking experiential guidelines at the task level, which can lead to beginners struggling to learn new tasks due to the lack of relevant experience. Moreover, the specific steps without guidelines are trivial and unsystematic, making it difficult to provide a clear tutorial. To address these problems, we present the GUIDE (Guideline-Guided) dataset, which contains 3.5K videos of 560 instructional tasks in 8 domains related to our daily life. Specifically, we annotate each instructional task with a guideline, representing a common pattern shared by all task-related videos. On this basis, we annotate systematic specific steps, including their associated guideline steps, specific step descriptions and timestamps. Our proposed benchmark consists of three sub-tasks to evaluate comprehension ability of models: (1) Step Captioning: models have to generate captions for specific steps from videos. (2) Guideline Summarization: models have to mine the common pattern in task-related videos and

Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into

Learning-based visual navigation for legged robots typically relies on continuous goal updates from hierarchical state estimation to provide a persistent directional reference. This reliance incurs additional sensory and computational overhead and deviates from fully end-to-end mobile autonomy. Furthermore, under partial observability, policies are prone to learn myopic behaviors, easily becoming trapped in dead ends and complex structural layouts. To address these limitations, we investigate a goal-initialized navigation setting, where the target is provided only once at the beginning of an episode, requiring the robot to operate based on intrinsic spatial memory without subsequent goal updates from external modules. In this work, we propose GUIDE, a fully end-to-end reinforcement learning framework designed to cultivate internal directional awareness. Specifically, GUIDE incorporates a spatial anchor predictor that leverages multi-frequency proprioceptive history to extract egomotion representations, thereby maintaining a persistent long-horizon spatial context for navigation. Concurrently, it utilizes raw depth streams to perceive local environmental geometry. We evaluate the pr

A robot guide dog has compelling advantages over animal guide dogs for its cost-effectiveness, potential for mass production, and low maintenance burden. However, despite the long history of guide dog robot research, previous studies were conducted with little or no consideration of how the guide dog handler and the guide dog work as a team for navigation. To develop a robotic guiding system that is genuinely beneficial to blind or visually impaired individuals, we performed qualitative research, including interviews with guide dog handlers and trainers and first-hand blindfold walking experiences with various guide dogs. Grounded on the facts learned from vivid experience and interviews, we build a collaborative indoor navigation scheme for a guide dog robot that includes preferred features such as speed and directional control. For collaborative navigation, we propose a semantic-aware local path planner that enables safe and efficient guiding work by utilizing semantic information about the environment and considering the handler's position and directional cues to determine the collision-free path. We evaluate our integrated robotic system by testing guide blindfold walking in in

This document provides a user guide for reducing UVIT data using CCDLAB. While CCDLAB offers a straightforward data reduction work-flow, users may encounter certain challenges that require additional guidance. This guide provides instructions by addressing common issues related to key processing steps, including WCS solutions and VIS drift tracking.

Machine learning datasets are powerful but unwieldy. Despite the fact that large datasets commonly contain problematic material--whether from a technical, legal, or ethical perspective--datasets are valuable resources when handled carefully and critically. A Critical Field Guide for Working with Machine Learning Datasets suggests practical guidance for conscientious dataset stewardship. It offers questions, suggestions, strategies, and resources for working with existing machine learning datasets at every phase of their lifecycle. It combines critical AI theories and applied data science concepts, explained in accessible language. Equipped with this understanding, students, journalists, artists, researchers, and developers can be more capable of avoiding the problems unique to datasets. They can also construct more reliable, robust solutions, or even explore new ways of thinking with machine learning datasets that are more critical and conscientious.

A light guide is an essential part of many scintillator counters and light collection systems. Our main interest is a light guide for a thin wide scintillator which has high light transmission while converting the area of the light source to the shape of a photo-detector. We propose a variation of the light guide which avoids a 90$\rm ^o$ twist of the strips, reduces the length of the light pipe, and reduces the complexity of production. Detailed Monte Carlo simulation studies have been performed for a 3-strip S-shaped light-guide system.

This article serves as a study guide for the $\ell^2$ decoupling theorem for the paraboloid originally proved by Bourgain and Demeter. Given its popularity and importance, many expositions about the $\ell^2$ decoupling theorem already exist. Our study guide is intended to complement and combine these existing resources in order to provide a more gentle introduction to the subject.

An alternating gradient electric guide provides a way to transport a wide variety of polar molecules, including those in high-field seeking states. We investigate the motion of polar molecules in such a guide by measuring the transmission of CaF molecules in their high-field seeking ground state, with the guide operating at a variety of switching frequencies and voltages. We model the guide using analytical and numerical techniques and compare the predictions of these models to the experimental results and to one another. The analytical results are approximate, but provide simple and useful estimates for the maximum phase-space acceptance of the guide and for the switching frequency required. The numerical methods provide more accurate results over the full range of switching frequencies. Our investigation shows that, even when the fields are static, some high-field seeking molecules are able to pass through the guide on metastable trajectories. We show that the maximum possible transmission requires accurate alignment within the guide and between the guide and detector.

Semi-supervised domain adaptation aims to classify data belonging to a target domain by utilizing a related label-rich source domain and very few labeled examples of the target domain. Here, we propose a novel framework, Pred&Guide, which leverages the inconsistency between the predicted and the actual class labels of the few labeled target examples to effectively guide the domain adaptation in a semi-supervised setting. Pred&Guide consists of three stages, as follows (1) First, in order to treat all the target samples equally, we perform unsupervised domain adaptation coupled with self-training; (2) Second is the label prediction stage, where the current model is used to predict the labels of the few labeled target examples, and (3) Finally, the correctness of the label predictions are used to effectively weigh source examples class-wise to better guide the domain adaptation process. Extensive experiments show that the proposed Pred&Guide framework achieves state-of-the-art results for two large-scale benchmark datasets, namely Office-Home and DomainNet.

There is a significant body of work looking at the ethical considerations of large language models (LLMs): critiquing tools to measure performance and harms; proposing toolkits to aid in ideation; discussing the risks to workers; considering legislation around privacy and security etc. As yet there is no work that integrates these resources into a single practical guide that focuses on LLMs; we attempt this ambitious goal. We introduce 'LLM Ethics Whitepaper', which we provide as an open and living resource for NLP practitioners, and those tasked with evaluating the ethical implications of others' work. Our goal is to translate ethics literature into concrete recommendations and provocations for thinking with clear first steps, aimed at computer scientists. 'LLM Ethics Whitepaper' distils a thorough literature review into clear Do's and Don'ts, which we present also in this paper. We likewise identify useful toolkits to support ethical work. We refer the interested reader to the full LLM Ethics Whitepaper, which provides a succinct discussion of ethical considerations at each stage in a project lifecycle, as well as citations for the hundreds of papers from which we drew our recomm

Despite recent advances in large-scale text-to-image generative models, manipulating real images with these models remains a challenging problem. The main limitations of existing editing methods are that they either fail to perform with consistent quality on a wide range of image edits or require time-consuming hyperparameter tuning or fine-tuning of the diffusion model to preserve the image-specific appearance of the input image. We propose a novel approach that is built upon a modified diffusion sampling process via the guidance mechanism. In this work, we explore the self-guidance technique to preserve the overall structure of the input image and its local regions appearance that should not be edited. In particular, we explicitly introduce layout-preserving energy functions that are aimed to save local and global structures of the source image. Additionally, we propose a noise rescaling mechanism that allows to preserve noise distribution by balancing the norms of classifier-free guidance and our proposed guiders during generation. Such a guiding approach does not require fine-tuning the diffusion model and exact inversion process. As a result, the proposed method provides a fas

Probabilistic programming languages aim to describe and automate Bayesian modeling and inference. Modern languages support programmable inference, which allows users to customize inference algorithms by incorporating guide programs to improve inference performance. For Bayesian inference to be sound, guide programs must be compatible with model programs. One pervasive but challenging condition for model-guide compatibility is absolute continuity, which requires that the model and guide programs define probability distributions with the same support. This paper presents a new probabilistic programming language that guarantees absolute continuity, and features general programming constructs, such as branching and recursion. Model and guide programs are implemented as coroutines that communicate with each other to synchronize the set of random variables they sample during their execution. Novel guide types describe and enforce communication protocols between coroutines. If the model and guide are well-typed using the same protocol, then they are guaranteed to enjoy absolute continuity. An efficient algorithm infers guide types from code so that users do not have to specify the types.

This article is a study guide for ``On the Hausdorff dimension of Furstenberg sets and orthogonal projections in the plane" by Orponen and Shmerkin. We begin by introducing Furstenberg set problem and exceptional set of projections and provide a summary of the proof with the core ideas.

We report the continuous or pulsed loading of a slow and cold atomic beam into a magnetic guide. In order to optimize the transfer into the guide, we have studied two coupling schemes. The first one is based on an auxiliary two-dimensional MOT that confines the atoms transversally before they enter the guide. However, for low atomic velocities, the atoms are strongly heated in the longitudinal direction. This limitation does not occur in the second coupling scheme which relies on magnetic confinement in the transfer zone. For this purpose, we have constructed a miniature magnetic guide located between the atomic source and the long magnetic guide. The latter scheme allows to inject atoms with velocities down to 70 cm/s into the guide.

This expository piece expounds on major themes and clarifies technical details of the paper "Kaufman and Falconer estimates for radial projections and a continuum version of Beck's theorem" of Orponen, Shmerkin, and Wang.

We study the role of the guide field in relativistic magnetic reconnection in a Harris current sheet of pair ($e^{\pm}$) plasmas, using linear theories and particle-in-cell (PIC) simulations. Two-dimensional PIC simulations exhibit the guide field dependence to the linear instabilities; the tearing or reconnection modes are relatively insensitive, while the relativistic drift-kink instability (RDKI), the fastest mode in a relativistic current sheet, is stabilized by the guide field. Particle acceleration in the nonlinear stage is also investigated. A three-dimensional PIC simulation demonstrates that the current sheet is unstable to the RDKI, although small reconnection occurs in the deformed current sheet. Another three-dimensional PIC simulation with a guide field demonstrates a completely different scenario. Secondary magnetic reconnection is triggered by nonlinear coupling of oblique instabilities, which we call the relativistic drift-sausage tearing instability. Therefore, particle acceleration by relativistic guide field reconnection occurs in three-dimensional configuration. Based on the plasma theories, we discuss an important role of the guide field: to enable non-thermal

We demonstrate a macroscopic magnetic guide for cold atoms with suppressed longitudinal field curvature which is highly desired for atom interferometry. The guide is based on macroscopic copper tape coils in a copropagating currents geometry, where the atoms are located between the coils few cm away from each surface. The symmetric geometry provides a much lower magnetic field curvature per fixed length that promises longer coherence time for atom interferometers. A double-tape design of each coil allows a smooth translation of guided atoms without addition of an external bias field. The guide is also immune from the current and thermal noise by virtue of the turns averaging and a large working distance, respectively. We present the experimental results of guide application to atom interferometry.

This manuscript is intended as an accompaniment to Guth's "A restriction estimate using polynomial partitioning". We begin by summarizing the core ideas of the proof, elaborating the history and development of the techniques therein. From there, we provide supplementary details on some of the standard methods and more technical arguments which may be unfamiliar or less accessible to readers not yet acquainted with the paper. We also provide a summary of some more recent developments since the publication of Guth's work.