机器人 / 具身智能

Estimation of User's World Model Using Graph2vec

Tatsuya Sakai, Takayuki Nagai

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

A Biologically-Inspired Dual Stream World Model

Arthur Juliani, Margaret Sereno

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

Variational Causal Dynamics: Discovering Modular World Models from Interventions

Anson Lei, Bernhard Schölkopf, Ingmar Posner

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

Cycle-Consistent World Models for Domain Independent Latent Imagination

Sidney Bender, Tim Joseph, Marius Zoellner

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

RLFlow: Optimising Neural Network Subgraph Transformation with World Models

Sean Parker, Sami Alabed, Eiko Yoneki

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

Comments 14 pages, 11 figures

The Impact of Negative Sampling on Contrastive Structured World Models

Ondrej Biza, Elise van der Pol, Thomas Kipf

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

Comments This work appeared at the ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception

Learning Domain Adaptation with Model Calibration for Surgical Report Generation in Robotic Surgery

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

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

Comments Accepted in ICRA 2021

Reinforcement learning with world model

Jingbin Liu, Xinyang Gu, Shuai Liu

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

Improving Generative Imagination in Object-Centric World Models

Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, Sungjin Ahn

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

Comments Accepted in ICML 2020

The Robotic Vision Scene Understanding Challenge

David Hall, Ben Talbot, Suman Raj Bista, Haoyang Zhang, Rohan Smith, Feras Dayoub, Niko Sünderhauf

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

Learning and Reasoning with the Graph Structure Representation in Robotic Surgery

Mobarakol Islam, Lalithkumar Seenivasan, Lim Chwee Ming, Hongliang Ren

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

Comments MICCAI 2020

Planning to Explore via Self-Supervised World Models

Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Pieter Abbeel, Danijar Hafner, Deepak Pathak

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

Comments Accepted at ICML 2020. Videos and code at https://ramanans1.github.io/plan2explore/

SCALOR: Generative World Models with Scalable Object Representations

Jindong Jiang, Sepehr Janghorbani, Gerard de Melo, Sungjin Ahn

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

Comments First two authors contributed equally. Published at ICLR 2020

Sepsis World Model: A MIMIC-based OpenAI Gym "World Model" Simulator for Sepsis Treatment

Amirhossein Kiani, Chris Wang, Angela Xu

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

Comments This project was done as a class project for CS221 at Stanford University

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction

C. Daniel Freeman, Luke Metz, David Ha

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

Comments To appear at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)

Deep Neuroevolution of Recurrent and Discrete World Models

Sebastian Risi, Kenneth O. Stanley

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

Continual Learning Using World Models for Pseudo-Rehearsal

Nicholas Ketz, Soheil Kolouri, Praveen Pilly

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

Learning Shared Dynamics with Meta-World Models

Lisheng Wu, Minne Li, Jun Wang

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

Recurrent World Models Facilitate Policy Evolution

David Ha, Jürgen Schmidhuber

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

Comments To appear at NIPS 2018, selected for an oral presentation. arXiv admin note: substantial text overlap with arXiv:1803.10122

World Models

David Ha, Jürgen Schmidhuber

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

Formalizing Preference Utilitarianism in Physical World Models

Caspar Oesterheld

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

Comments 14 pages, 3 figures

Revisiting the Othello World Model Hypothesis

Yifei Yuan, Anders Søgaard

专题命中 具身推理 ：world model(title,abstract)

Comments ICLR World Models Workshop

A General World Model with Poiesis: Poppers Three Worlds updated with Software

Walter Hehl

专题命中 具身推理 ：world model(title,abstract)

Comments 9 pages. 1 Figure of a world model with physics, software and Geist, Book published 2016 (in German) by Springer, Heidelberg, with the general fundamentals of Software for philosophy

Structured 4D Latent Predictive Model for Robot Planning

结构化4D潜在预测模型用于机器人规划

Zhiyi Li, Peilin Wu, Xiaoshen Han, Ruojin Cai, Yilun Du

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

AI总结 提出结构化4D潜在预测模型，在潜在空间中预测场景3D结构演化，实现3D一致的场景理解与机器人规划，在复杂操作任务中优于现有视频基规划器。

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

GameplayQA: 一种用于3D虚拟代理多视频理解的决策密集型视角同步评估框架

Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun

机构 * University of Southern California（南加州大学） 纠错

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

AI总结 GameplayQA通过密集标注多玩家3D游戏视频，构建了2.4K诊断QA对，评估代理感知与推理能力，揭示了前沿MLLM在时间同步、跨视频定位及决策密度处理上的不足。

Comments Accepted to the Annual Meeting of the Association for Computational Linguistics (ACL 2026)

A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding

Zhenyang Liu, Sixiao Zheng, Siyu Chen, Cairong Zhao, Longfei Liang, Xiangyang Xue, Yanwei Fu

机构 * Fudan University, Shanghai Innovation Institute（复旦大学） ； Zhejiang University（浙江大学） ； Tongji University（同济大学） ； NeuHelium Co., Ltd（NeuHelium公司） ； Fudan University（复旦大学） 纠错

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

O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning

Kaichun Mo, Yuzhe Qin, Fanbo Xiang, Hao Su, Leonidas Guibas

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

Comments to appear in CoRL 2021

A JEPA-Based Field-Layer World Model for Bridging Channel Prediction and Estimation

一种基于JEPA的场层世界模型，用于衔接信道预测与估计

Yuzhi Yang, Brahim Mefgouda, Hang Zou, Lina Bariah, Anis Bara, Yuhuan Lu, Hao Zhang, MérouaneDebbah

专题命中 具身推理 ：world model(title,abstract)

AI总结 该研究针对MIMO-OFDM无线系统中CSI预测鲁棒性差的问题，提出基于JEPA的场层世界模型，通过多尺度对齐策略实现跨频段重构，显著提升了波束成形增益。

Comments submitted to IEEE trans

Metric Non-Collapse in Learned World Models for Control: Approximation Theory, Finite-Sample Geometric Guarantees, and Deterministic Planning Transfer

用于控制的学习型世界模型中的度量非崩溃：逼近理论、有限样本几何保证与确定性规划迁移

Alain Bensoussan, Minh-Nhat Phung, Minh-Binh Tran

专题命中 具身推理 ：world model(title,abstract)

AI总结 该研究为非线性确定性控制系统的学习型世界模型构建三部分数学理论，含逼近理论、有限样本几何保证及确定性规划迁移方法，通过数值实验验证了相关方法的有效性。

Beyond Static Forecasting: Unleashing the Power of World Models for Mobile Traffic Extrapolation

超越静态预测：利用世界模型进行移动交通外推

Xiaoqian Qi, Haoye Chai, Yue Wang, Yong Li

专题命中 具身推理 ：world model(title,abstract)

AI总结 本文提出MobiWM世界模型，用于移动网络中的移动交通外推，通过融合多模态环境上下文和编码动作，提升空间理解，实验表明其在所有评估场景中均取得最佳分布保真度。