机器人 / 具身智能

Collaborating with language models for embodied reasoning

Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, Arun Ahuja, Sheila Babayan, Felix Hill, Rob Fergus

专题命中 具身推理 ：embodied agent(abstract)；分类 cs.AI、cs.LG

Comments Presented at NeurIPS 2022 Language and Reinforcement Learning Workshop (best paper) and NeurIPS 2022 Foundation Models for Decision Making Workshop. 4 pages main; 14 pages total (including references and appendix); 3 figures

Learning to Act with Affordance-Aware Multimodal Neural SLAM

Zhiwei Jia, Kaixiang Lin, Yizhou Zhao, Qiaozi Gao, Govind Thattai, Gaurav Sukhatme

专题命中 具身推理 ：navigation(abstract)；分类 cs.RO、cs.AI

Comments Accepted by IROS 2022

Learning Robust Dynamics through Variational Sparse Gating

Arnav Kumar Jain, Shivakanth Sujit, Shruti Joshi, Vincent Michalski, Danijar Hafner, Samira Ebrahimi-Kahou

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

Review on Panoramic Imaging and Its Applications in Scene Understanding

Shaohua Gao, Kailun Yang, Hao Shi, Kaiwei Wang, Jian Bai

专题命中 具身推理 ：robotics(abstract)；分类 cs.RO、cs.CV

Comments Accepted to IEEE Transactions on Instrumentation and Measurement. 34 pages, 15 figures, 420 references

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

Beren Millidge, Yuhang Song, Tommaso Salvatori, Thomas Lukasiewicz, Rafal Bogacz

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

Comments 21/07/22 initial upload (finally); 03/08/22 revisions

Modelling non-reinforced preferences using selective attention

Noor Sajid, Panagiotis Tigas, Zafeirios Fountas, Qinghai Guo, Alexey Zakharov, Lancelot Da Costa

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

Comments 4 pages, 3 figures - Workshop Track: 1st Conference on Lifelong Learning Agents, 2022

Robust deep learning-based semantic organ segmentation in hyperspectral images

Silvia Seidlitz, Jan Sellner, Jan Odenthal, Berkin Özdemir, Alexander Studier-Fischer, Samuel Knödler, Leonardo Ayala, Tim J. Adler, Hannes G. Kenngott, Minu Tizabi, Martin Wagner, Felix Nickel, Beat P. Müller-Stich, Lena Maier-Hein

专题命中 具身推理 ：robotics(abstract)；分类 cs.CV、cs.LG

Comments The first two authors (Silvia Seidlitz and Jan Sellner) contributed equally to this paper

Journal ref Medical Image Analysis, Volume 80, 2022, 102488, ISSN 1361-8415

Conditional Object-Centric Learning from Video

Thomas Kipf, Gamaleldin F. Elsayed, Aravindh Mahendran, Austin Stone, Sara Sabour, Georg Heigold, Rico Jonschkowski, Alexey Dosovitskiy, Klaus Greff

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

Comments Published at ICLR 2022. Project page at https://slot-attention-video.github.io/

LanguageRefer: Spatial-Language Model for 3D Visual Grounding

Junha Roh, Karthik Desingh, Ali Farhadi, Dieter Fox

专题命中 具身推理 ：robotics(abstract)；分类 cs.RO、cs.CV

Comments 11 pages, 3 figures

Dream to Explore: Adaptive Simulations for Autonomous Systems

Zahra Sheikhbahaee, Dongshu Luo, Blake VanBerlo, S. Alex Yun, Adam Safron, Jesse Hoey

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

Indoor Semantic Scene Understanding using Multi-modality Fusion

Muraleekrishna Gopinathan, Giang Truong, Jumana Abu-Khalaf

专题命中 具身推理 ：robotic(abstract)；分类 cs.AI、cs.CV

Comments International Conference on Digital Image Computing: Techniques and Applications (DICTA), 5 figures, 8 pages

Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?

Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat

专题命中 具身推理 ：robotics(abstract)；分类 cs.CV、cs.LG

Visual-Semantic Graph Attention Networks for Human-Object Interaction Detection

Zhijun Liang, Juan Rojas, Junfa Liu, Yisheng Guan

专题命中 具身推理 ：robotics(abstract)；分类 cs.CV、cs.LG

Comments 7 pages, 4 figures, 3 tables

Towards General Purpose Geometry-Preserving Single-View Depth Estimation

Mikhail Romanov, Nikolay Patatkin, Anna Vorontsova, Sergey Nikolenko, Anton Konushin, Dmitry Senyushkin

专题命中 具身推理 ：robotics(abstract)；分类 cs.CV、cs.LG

Planning from Pixels using Inverse Dynamics Models

Keiran Paster, Sheila A. McIlraith, Jimmy Ba

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

Comments 9 pages, 4 figures

Image Segmentation Using Deep Learning: A Survey

Shervin Minaee, Yuri Boykov, Fatih Porikli, Antonio Plaza, Nasser Kehtarnavaz, Demetri Terzopoulos

专题命中 具身推理 ：robotic(abstract)；分类 cs.CV、cs.LG

A Model of Fast Concept Inference with Object-Factorized Cognitive Programs

Daniel P. Sawyer, Miguel Lázaro-Gredilla, Dileep George

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

Comments 7 pages, 4 figures, 5 tables, to be presented at CogSci 2020

Human-like general language processing

Feng Qi, Guanjun Jiang

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

Who2com: Collaborative Perception via Learnable Handshake Communication

Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma, Nathan Glaser, Chia-Wen Kuo, Zsolt Kira

专题命中 具身推理 ：robotics(abstract)；分类 cs.RO、cs.CV

Comments Accepted to ICRA 2020

Fine-grained Qualitative Spatial Reasoning about Point Positions

Sören Schwertfeger

专题命中 具身推理 ：robotic(abstract)；分类 cs.RO、cs.AI

Comments Diploma Thesis of Sören Schwertfeger at University of Bremen. August 2005

Structural Pruning in Deep Neural Networks: A Small-World Approach

Gokul Krishnan, Xiaocong Du, Yu Cao

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

Multi-view Clustering with the Cooperation of Visible and Hidden Views

Zhaohong Deng, Ruixiu Liu, Te Zhang, Peng Xu, Kup-Sze Choi, Bin Qin, Shitong Wang

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

Comments This paper has been submitted to IEEE TKDE in Jun. 2019

AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection

Thanh-Toan Do, Anh Nguyen, Ian Reid

专题命中 具身推理 ：robotic(abstract)；分类 cs.RO、cs.CV

Comments In ICRA 2018

Target Curricula via Selection of Minimum Feature Sets: a Case Study in Boolean Networks

Shannon Fenn, Pablo Moscato

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

Comments Accepted for publication in JMLR issue 18

Predicting Deeper into the Future of Semantic Segmentation

Pauline Luc, Natalia Neverova, Camille Couprie, Jakob Verbeek, Yann LeCun

专题命中 具身推理 ：robotics(abstract)；分类 cs.CV、cs.LG

Comments Accepted to ICCV 2017. Supplementary material available on the authors' webpages

A Base Camp for Scaling AI

C. J. C. Burges, T. Hart, Z. Yang, S. Cucerzan, R. W. White, A. Pastusiak, J. Lewis

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

Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure

想象的展开是运动学的，而非动力学的：对长期世界模型失败的诊断

Finn Rasmus Schäfer, Korbinian Moller, Yuan Gao, Christian Oefinger, Sebastian Schmidt, Johannes Betz

机构 * Autonomous Vehicle Systems Lab（自动驾驶车辆系统实验室） ； Technical University of Munich（慕尼黑技术大学） ； Data Analytics and Machine Learning Group（数据分析与机器学习小组） 纠错

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

AI总结 研究针对世界模型长期失败问题，提出用运动学与动力学重新构建的方法，通过想象的运动学一致性误差（iKCE）及扰动协议进行诊断，在DreamerV3检查点实例化，区分了运动学与动力学想象，揭示模型长期失败特征。

Comments 9 Pages Workshop Paper accepted at RSS Robot World Model Workshop 2026

Coupled Particle Filters for Robust Affordance Estimation

耦合粒子滤波器用于鲁棒的 affordance 估计

Patrick Lowin, Vito Mengers, Oliver Brock

机构 * Robotics and Biology Laboratory, Technische Universität Berlin（技术大学柏林机器人与生物学实验室） ； Robotics Institute Germany（德国机器人研究所） ； Science of Intelligence (SCIoI), Cluster of Excellence, Berlin, Germany（智能科学（SCIoI），卓越中心，柏林，德国） 纠错

专题命中 具身推理 ：robotic(abstract)；分类 cs.RO；robotics(comments)

AI总结 本文提出耦合递归估计器用于估计 affordance 的可抓取和可移动区域，通过双向信息交换提升鲁棒性和精度，在真实数据集上优于现有方法。

Comments Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2026

RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models

RetoVLA: 通过重用寄存器令牌在视觉-语言-动作模型中实现空间推理

Jiyeon Koo, Taewan Cho, Hyunjoon Kang, Eunseom Pyo, Tae Gyun Oh, Taeryang Kim, Andrew Jaeyong Choi

机构 * School of Computing, Gachon University（高丽大学计算机学院） 纠错

专题命中 具身推理 ：robotic(abstract)；分类 cs.RO；robotics(journal_ref)

AI总结 RetoVLA通过重用注册令牌提升视觉-语言-动作模型的空间推理能力，实验显示在7自由度机械臂任务中平均成功率提升17.1%。

Journal ref 2026 IEEE International Conference on Robotics and Automation (ICRA)

ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving

ImagiDrive: 一种用于自动驾驶的统一想象与规划框架

Jingyu Li, Bozhou Zhang, Xin Jin, Jiankang Deng, Xiatian Zhu, Li Zhang

机构 * School of Data Science, Fudan University（复旦大学数据科学学院） ； Shanghai Innovation Institute（上海创新研究院） ； Eastern Institute of Technology（技术东院） ； Imperial College London（伦敦帝国理工学院） ； University of Surrey（萨里大学） 纠错

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

AI总结 ImagiDrive通过整合视觉-语言模型和驾驶世界模型，实现自动驾驶中的统一想象与规划循环，提升场景生成和决策预测的准确性与效率。

Comments Accepted for publication in 2026 IEEE International Conference on Robotics and Automation (ICRA)