检索结果-内蒙古大学图书馆

PinchCatcher: Enabling Multi-selection for Gaze+Pinch 25

学校读者我要写书评

暂无评论

PinchCatcher: Enabling Multi-selection for Gaze+Pinch

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Kim, Jinwook Park, Sangmin Zhou, Qiushi Gonzalez-Franco, Mar Lee, Jeongmi Pfeuffer, Ken Graduate School of Culture Technology Kaist Daejeon South Korea Department of Computer Science Aarhus University Aarhus Denmark Google Seattle WA United States

ISBN: (纸本)9798400713941

This paper investigates multi-selection in XR interfaces based on eye and hand interaction. We propose enabling multi-selection using different variations of techniques that combine gaze with a semi-pinch gesture, allowing users to select multiple objects, while on the way to a full-pinch. While our exploration is based on the semi-pinch mode for activating a quasi-mode, we explore four methods for confirming subselections in multi-selection mode, varying in effort and complexity: dwell-time (SemiDwell), swipe (SemiSwipe), tilt (SemiTilt), and non-dominant hand input (SemiNDH), and compare them to a baseline technique. In the user study, we evaluate their effectiveness in reducing task completion time, errors, and effort. The results indicate the strengths and weaknesses of each technique, with SemiSwipe and SemiDwell as the most preferred methods by participants. We also demonstrate their utility in file managing and RTS gaming application scenarios. This study provides valuable insights to advance 3D input systems in XR. © 2025 Copyright held by the owner/author(s).

关键词： Extended Reality Eye-Hand interaction Gaze Gestures Grouping Selection

Corrective Retrieval Augmented Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Shi-Qi Gu, Jia-Chen Zhu, Yun Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China Department of Computer Science University of California Los Angeles United States Google DeepMind United Kingdom

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. Specifically, a lightweight retrieval evaluator is designed to assess the overall quality of retrieved documents for a query, returning a confidence degree based on which different knowledge retrieval actions can be triggered. Since retrieval from static and limited corpora can only return suboptimal documents, large-scale web searches are utilized as an extension for augmenting the retrieval results. Besides, a decompose-then-recompose algorithm is designed for retrieved documents to selectively focus on key information and filter out irrelevant information in them. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches. Experiments on four datasets covering short- and long-form generation tasks show that CRAG can significantly improve the performance of RAG-based approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Structured Query Language

Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Oscar Harrison, James Sohl-Dickstein, Jascha Smith, Virginia Metz, Luke Machine Learning Department School of Computer Science Carnegie Mellon University United States Google DeepMind United Kingdom OpenAI

Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or blackbox characteristics. In such scenarios, online evolution strategies methods are a more capable alternative, while being more parallelizable than vanilla evolution strategies (ES) by interleaving partial unrolls and gradient updates. In this work, we propose a general class of unbiased online evolution strategies methods. We analytically and empirically characterize the variance of this class of gradient estimators and identify the one with the least variance, which we term Noise-Reuse Evolution Strategies (NRES). Experimentally3, we show NRES results in faster convergence than existing AD and ES methods in terms of wall-clock time and number of unroll steps across a variety of applications, including learning dynamical systems, meta-training learned optimizers, and reinforcement learning. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Online Learning for Obstacle Avoidance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Snyder, David Booker, Meghan Simon, Nathaniel Xia, Wenhan Suo, Daniel Hazan, Elad Majumdar, Anirudha Lab Princeton University United States Department of Computer Science Princeton University United States Google DeepMind United Kingdom

We approach the fundamental problem of obstacle avoidance for robotic systems via the lens of online learning. In contrast to prior work that either assumes worst-case realizations of uncertainty in the environment or a stationary stochastic model of uncertainty, we propose a method that is efficient to implement and provably grants instance-optimality with respect to perturbations of trajectories generated from an open-loop planner (in the sense of minimizing worst-case regret). The resulting policy adapts online to realizations of uncertainty and provably compares well with the best obstacle avoidance policy in hindsight from a rich class of policies. The method is validated in simulation on a dynamical system environment and compared to baseline open-loop planning and robust Hamilton-Jacobi reachability techniques. Further, it is implemented on a hardware example where a quadruped robot traverses a dense obstacle field and encounters input disturbances due to time delays, model uncertainty, and dynamics nonlinearities. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic models

Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zha, Lihan Cui, Yuchen Lin, Li-Heng Kwon, Minae Arenas, Montserrat Gonzalez Zeng, Andy Xia, Fei Sadigh, Dorsa Computer Science Department Stanford University StanfordCA United States Google Deepmind Mountain ViewCA United States

Today’s robot policies exhibit subpar performance when faced with the challenge of generalizing to novel environments. Human corrective feedback is a crucial form of guidance to enable such generalization. However, adapting to and learning from online human corrections is a non-trivial endeavor: not only do robots need to remember human feedback over time to retrieve the right information in new settings and reduce the intervention rate, but also they would need to be able to respond to feedback that can be arbitrary corrections about high-level human preferences to low-level adjustments to skill parameters. In this work, we present Distillation and Retrieval of Online Corrections (DROC), a large language model (LLM)based system that can respond to arbitrary forms of language feedback, distill generalizable knowledge from corrections, and retrieve relevant past experiences based on textual and visual similarity for improving performance in novel settings. DROC is able to respond to a sequence of online language corrections that address failures in both high-level task plans and low-level skill primitives. We demonstrate that DROC effectively distills the relevant information from the sequence of online corrections in a knowledge base and retrieves that knowledge in settings with new task or object instances. DROC outperforms other techniques that directly generate robot code via LLMs [1] by using only half of the total number of corrections needed in the first round and requires little to no corrections after two iterations. We show further results and videos on our project website: https://***/***/droc. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

On imitation in mean-field games 23

学校读者我要写书评

暂无评论

On imitation in mean-field games

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Giorgia Ramponi Pavel Kolev Olivier Pietquin Niao He Mathieu Laurière Matthieu Geist ETH AI Center Zurich Max Planck Institute for Intelligent Systems Tübingen Germany Google DeepMind ETH Zurich Department of Computer Science Google DeepMind and Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning NYU Shanghai

We explore the problem of imitation learning (IL) in the context of mean-field games (MFGs), where the goal is to imitate the behavior of a population of agents following a Nash equilibrium policy according to some unknown payoff function. IL in MFGs presents new challenges compared to single-agent IL, particularly when both the reward function and the transition kernel depend on the population distribution. In this paper, departing from the existing literature on IL for MFGs, we introduce a new solution concept called the Nash imitation gap. Then we show that when only the reward depends on the population distribution, IL in MFGs can be reduced to single-agent IL with similar guarantees. However, when the dynamics is population-dependent, we provide a novel upper-bound that suggests IL is harder in this setting. To address this issue, we propose a new adversarial formulation where the reinforcement learning problem is replaced by a mean-field control (MFC) problem, suggesting progress in IL within MFGs may have to build upon MFC.

关键词：

Agricultural Landscape Understanding At Country-Scale

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dua, Radhika Saxena, Nikita Agarwal, Aditi Wilson, Alex Singh, Gaurav Tran, Hoang Deshpande, Ishan Kaur, Amandeep Aggarwal, Gaurav Nath, Chandan Basu, Arnab Batchu, Vishal Holla, Sharath Kurle, Bindiya Missura, Olana Aggarwal, Rahul Garg, Shubhika Shah, Nishi Singh, Avneet Tewari, Dinesh Dondzik, Agata Adsul, Bharat Sohoni, Milind Praveen, Asim Rama Dangi, Aaryan Kadivar, Lisan Abhishek, E. Sudhansu, Niranjan Hattekar, Kamlakar Datar, Sameer Chaithanya, Musty Krishna Reddy, Anumas Ranjith Kumar, Aashish Tirumala, Betala Laxmi Talekar, Alok Google DeepMind India Google United States Department of Computer Science IIT Bombay India Department of Land Records State Government of Maharashtra India TeamUp India Department of Agriculture State Government of Telangana India Department of Information Technology Electronics & Communication State Government of Telangana India

Agricultural landscapes are quite complex, especially in the Global South where fields are smaller, and agricultural practices are more varied. In this paper we report on our progress in digitizing the agricultural landscape (natural and man-made) in our study region of India. We use high resolution imagery and a UNet style segmentation model to generate the first of its kind national-scale multi-class panoptic segmentation output. Through this work we have been able to identify individual fields across 151.7M hectares, and delineating key features such as water resources and vegetation. We share how this output was validated by our team and externally by downstream users, including some sample use cases that can lead to targeted data driven decision making. We believe this dataset will contribute towards digitizing agriculture by generating the foundational baselayer. © 2024, CC BY-NC-SA.

关键词：

Position: considerations for differentially private learning with large-scale public pretraining 24

学校读者我要写书评

暂无评论

Position: considerations for differentially private learning...

Proceedings of the 41st International Conference on Machine Learning

作者： Florian Tramèr Gautam Kamath Nicholas Carlini Department of Computer Science ETH Zürich Zürich Switzerland Cheriton School of Computer Science University of Waterloo Waterloo Ontario Canada and Vector Institute Toronto Ontario Canada Google DeepMind Mountain View

The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of nonprivate models pretrained on large public datasets. We critically review this approach. We primarily question whether the use of large Web-scraped datasets should be viewed as differential-privacy-preserving. We further scrutinize whether existing machine learning benchmarks are appropriate for measuring the ability of pretrained models to generalize to sensitive domains. Finally, we observe that reliance on large pretrained models may lose other forms of privacy, requiring data to be out-sourced to a more compute-powerful third party.

关键词：

Learning energy-based prior model with diffusion-amortized MCMC 23

学校读者我要写书评

暂无评论

Learning energy-based prior model with diffusion-amortized M...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Peiyu Yu Yaxuan Zhu Sirui Xie Xiaojian Ma Ruiqi Gao Song-Chun Zhu Ying Nian Wu UCLA Department of Statistics UCLA Department of Computer Science UCLA Department of Computer Science and Beijing Institute for General Artificial Intelligence (BIGAI) Google DeepMind Beijing Institute for General Artificial Intelligence (BIGAI)

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in the field of generative modeling due to its flexibility in the formulation and strong modeling power of the latent space. However, the common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress; the degenerate MCMC sampling quality in practice often leads to degraded generation quality and instability in training, especially with highly multimodal and/or high-dimensional target distributions. To remedy this sampling issue, in this paper we introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it. We provide theoretical evidence that the learned amortization of MCMC is a valid long-run MCMC sampler. Experiments on several image modeling benchmark datasets demonstrate the superior performance of our method compared with strong counterparts. Code and data available at https://***/yuPeiyu98/Diffusion-Amortized-MCMC.

关键词：