机器人 / 具身智能 - arXivDaily 专题

2306.14824 2023-07-14 cs.CL cs.CV 57%

Kosmos-2: Grounding Multimodal Large Language Models to the World

Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, Furu Wei

专题命中具身推理：world model(abstract)；分类 cs.CV

Comments 20 pages

2304.10950 2023-06-22 cs.CV 57%

Factored Neural Representation for Scene Understanding

Yu-Shiang Wong, Niloy J. Mitra

专题命中具身推理：manipulation(abstract)；分类 cs.CV

2306.11448 2023-06-21 cs.RO 57%

Prepare the Chair for the Bear! Robot Imagination of Sitting Affordance to Reorient Previously Unseen Chairs

Xin Meng, Hongtao Wu, Sipu Ruan, Gregory S. Chirikjian

专题命中具身推理：manipulation(abstract)；分类 cs.RO

2306.11297 2023-06-21 cs.LG 57%

Decentralized Quantum Federated Learning for Metaverse: Analysis, Design and Implementation

Dev Gurung, Shiva Raj Pokhrel, Gang Li

专题命中具身推理：world model(abstract)；分类 cs.LG

2306.02021 2023-06-06 cs.CV 57%

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method

Yifei Gao, Zhiyu Lin, Yunfan Yang, Jitao Sang

专题命中具身推理：world model(abstract)；分类 cs.CV

Comments 14 pages, 8 figures, 13 tables

2302.14045 2023-03-02 cs.CL cs.CV 57%

Language Is Not All You Need: Aligning Perception with Language Models

Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Barun Patra, Qiang Liu, Kriti Aggarwal, Zewen Chi, Johan Bjorck, Vishrav Chaudhary, Subhojit Som, Xia Song, Furu Wei

专题命中具身推理：world model(abstract)；分类 cs.CV

2010.08869 2023-02-07 cs.AI 57%

Task Scoping: Generating Task-Specific Abstractions for Planning in Open-Scope Models

Michael Fishman, Nishanth Kumar, Cameron Allen, Natasha Danas, Michael Littman, Stefanie Tellex, George Konidaris

专题命中具身推理：world model(abstract)；分类 cs.AI

2301.07499 2023-01-19 cs.CV 57%

A Comprehensive Review of Modern Object Segmentation Approaches

Yuanbo Wang, Unaiza Ahsan, Hanyan Li, Matthew Hagen

专题命中具身推理：robotics(abstract)；分类 cs.CV

Comments 173 pages, 49 figures, published in Foundations and Trends in Computer Graphics and Vision on 10/4/22. Authors retain copyright

Journal ref Foundations and Trends in Computer Graphics and Vision: Vol. 13: No. 2-3, pp 111-283

2003.04315 2023-01-19 cs.IR cs.LG stat.ML 57%

LIMEADE: From AI Explanations to Advice Taking

Benjamin Charles Germain Lee, Doug Downey, Kyle Lo, Daniel S. Weld

专题命中具身推理：world model(abstract)；分类 cs.LG

Comments 18 pages, 7 figures

2212.11511 2022-12-23 cs.CV 57%

Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding

Mengya Xu, Mobarakol Islam, Ben Glocker, Hongliang Ren

专题命中具身推理：robotic(abstract)；分类 cs.CV

Comments 12 pages

Journal ref IEEE Transactions on Automation Science and Engineering, 2022

2211.13425 2022-11-28 cs.RO 57%

Automated Driving Systems Data Acquisition and Processing Platform

Xin Xia, Zonglin Meng, Xu Han, Hanzhao Li, Takahiro Tsukiji, Runsheng Xu, Zhaoliang Zhang, Jiaqi Ma

专题命中具身推理：world model(abstract)；分类 cs.RO

2211.10831 2022-11-22 cs.LG 57%

Joint Embedding Predictive Architectures Focus on Slow Features

Vlad Sobal, Jyothir S, Siddhartha Jalagam, Nicolas Carion, Kyunghyun Cho, Yann LeCun

专题命中具身推理：world model(abstract)；分类 cs.LG

Comments 4 pages (3 figures) short paper for SSL Theory and Practice workshop at NeurIPS 2022. Code is available at NeurIPS_2022" target="_blank" rel="noopener">https://github.com/vladisai/JEPA_SSL_NeurIPS_2022

2210.09897 2022-10-19 q-fin.TR cs.GT cs.LG q-fin.CP 57%

Learning to simulate realistic limit order book markets from data as a World Agent

Andrea Coletta, Aymeric Moulin, Svitlana Vyetrenko, Tucker Balch

专题命中具身推理：world model(abstract)；分类 cs.LG

2208.02938 2022-08-08 cs.AI cs.PL 57%

Abstract Interpretation for Generalized Heuristic Search in Model-Based Planning

Tan Zhi-Xuan, Joshua B. Tenenbaum, Vikash K. Mansinghka

专题命中具身推理：world model(abstract)；分类 cs.AI

Comments 4 pages, 2 figures. Presented at the ICML 2022 Workshop on Beyond Bayes: Paths Towards Universal Reasoning Systems

2204.02548 2022-07-20 cs.CV 57%

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

Yuyang Zhao, Zhun Zhong, Na Zhao, Nicu Sebe, Gim Hee Lee

专题命中具身推理：world model(abstract)；分类 cs.CV

Comments ECCV 2022

2203.13762 2022-06-23 cs.AI cs.IT math.IT 57%

A World-Self Model Towards Understanding Intelligence

Yutao Yue

专题命中具身推理：world model(abstract)；分类 cs.AI

Comments 21 pages, 5 figures

Journal ref IEEE Access, vol. 10, pp. 63034-63048, 2022

2109.13410 2022-06-06 cs.CV 57%

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

Yiyi Liao, Jun Xie, Andreas Geiger

专题命中具身推理：robotics(abstract)；分类 cs.CV

Comments arXiv admin note: text overlap with arXiv:1511.03240

2111.02444 2022-05-17 cs.CV 57%

Panoptic 3D Scene Reconstruction From a Single RGB Image

Manuel Dahnert, Ji Hou, Matthias Nießner, Angela Dai

专题命中具身推理：robotics(abstract)；分类 cs.CV

Comments Video: https://youtu.be/YVxRNHmd5SA, Project Page: https://manuel-dahnert.com/research/panoptic-reconstruction

2203.01507 2022-03-04 cs.MA cs.RO cs.SY eess.SY 57%

SMA-NBO: A Sequential Multi-Agent Planning with Nominal Belief-State Optimization in Target Tracking

Tianqi Li, Lucas W. Krakow, Swaminathan Gopalswamy

专题命中具身推理：world model(abstract)；分类 cs.RO

2109.05566 2022-01-11 cs.CV 57%

PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds

Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang

专题命中具身推理：robotic(abstract)；分类 cs.CV

Comments Code: https://github.com/OPEN-AIR-SUN/PQ-Transformer

2004.04630 2021-12-13 cs.CV 57%

Where Does It End? -- Reasoning About Hidden Surfaces by Object Intersection Constraints

Michael Strecke, Joerg Stueckler

专题命中具身推理：robotics(abstract)；分类 cs.CV

Comments IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, Project page: https://cosection.is.tue.mpg.de/, Source code: https://github.com/EmbodiedVision/cosection

Journal ref IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020

2111.08434 2021-11-17 cs.CV 57%

Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion

Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha, Om J Omer, Sreenivas Subramoney

专题命中具身推理：robotics(abstract)；分类 cs.CV

2110.01997 2021-10-06 cs.CV 57%

Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images

Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc Van Gool

专题命中具身推理：navigation(abstract)；分类 cs.CV

Comments ICCV 2021

2007.12868 2021-09-28 cs.CV 57%

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets

Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, Yuhan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Zexiang Xu, Hong-Xing Yu, Kalyan Sunkavalli, Miloš Hašan, Ravi Ramamoorthi, Manmohan Chandraker

专题命中具身推理：robotics(abstract)；分类 cs.CV

2109.11453 2021-09-24 cs.CV 57%

Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

Xuemeng Yang, Hao Zou, Xin Kong, Tianxin Huang, Yong Liu, Wanlong Li, Feng Wen, Hongbo Zhang

专题命中具身推理：robotics(abstract)；分类 cs.CV

Comments 8 pages, 4 figures, accepted by The 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems

2108.03658 2021-08-10 cs.CV 57%

One-Shot Object Affordance Detection in the Wild

Wei Zhai, Hongchen Luo, Jing Zhang, Yang Cao, Dacheng Tao

专题命中具身推理：manipulation(abstract)；分类 cs.CV

2107.11091 2021-07-26 cs.CV eess.IV 57%

Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation

Mengya Xu, Mobarakol Islam, Chwee Ming Lim, Hongliang Ren

专题命中具身推理：robotic(abstract)；分类 cs.CV

Comments Accepted in MICCAI 2021

2106.14747 2021-06-29 cs.CV 57%

One-Shot Affordance Detection

Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, Dacheng Tao

专题命中具身推理：manipulation(abstract)；分类 cs.CV

2011.08424 2021-06-24 cs.RO 57%

Deep Affordance Foresight: Planning Through What Can Be Done in the Future

Danfei Xu, Ajay Mandlekar, Roberto Martín-Martín, Yuke Zhu, Silvio Savarese, Li Fei-Fei

专题命中具身推理：manipulation(abstract)；分类 cs.RO

Comments ICRA 2021

2105.07284 2021-05-24 q-bio.NC cs.AI 57%

A brain basis of dynamical intelligence for AI and computational neuroscience

Joseph D. Monaco, Kanaka Rajan, Grace M. Hwang

专题命中具身推理：world model(abstract)；分类 cs.AI

Comments Perspective article: 24 pages, 3 figures, 1 display box

1. 具身推理 3100 篇

Kosmos-2: Grounding Multimodal Large Language Models to the World

Factored Neural Representation for Scene Understanding

Prepare the Chair for the Bear! Robot Imagination of Sitting Affordance to Reorient Previously Unseen Chairs

Decentralized Quantum Federated Learning for Metaverse: Analysis, Design and Implementation

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method

Language Is Not All You Need: Aligning Perception with Language Models

Task Scoping: Generating Task-Specific Abstractions for Planning in Open-Scope Models

A Comprehensive Review of Modern Object Segmentation Approaches

LIMEADE: From AI Explanations to Advice Taking

Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding

Automated Driving Systems Data Acquisition and Processing Platform

Joint Embedding Predictive Architectures Focus on Slow Features

Learning to simulate realistic limit order book markets from data as a World Agent

Abstract Interpretation for Generalized Heuristic Search in Model-Based Planning

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

A World-Self Model Towards Understanding Intelligence

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

Panoptic 3D Scene Reconstruction From a Single RGB Image

SMA-NBO: A Sequential Multi-Agent Planning with Nominal Belief-State Optimization in Target Tracking

PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds

Where Does It End? -- Reasoning About Hidden Surfaces by Object Intersection Constraints

Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion

Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets

Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

One-Shot Object Affordance Detection in the Wild

Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation

One-Shot Affordance Detection

Deep Affordance Foresight: Planning Through What Can Be Done in the Future

A brain basis of dynamical intelligence for AI and computational neuroscience