机器人 / 具身智能

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents

Hang Su, Jun Luo, Chang Liu, Xiao Yang, Yichi Zhang, Yinpeng Dong, Jun Zhu

机构 * Dept. of Comp. Sci. & Tech.（计算机科学与技术系） ； College of AI（人工智能学院） ； Institute for AI（人工智能研究院） ； BNRist Center（BNRist中心） ； THBI Lab（THBI实验室） ； Tsinghua-Bosch Joint Center for ML（清华大学-博世联合机器学习中心） ； Tsinghua University（清华大学） 纠错

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

Comments 18 pages

ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models

Zixun Fang, Kai Zhu, Zhiheng Liu, Yu Liu, Wei Zhai, Yang Cao, Zheng-Jun Zha

机构 * USTC（中国科学技术大学） ； TongYi Lab（通义实验室） ； HKU（香港大学） 纠错

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

Comments https://becauseimbatman0.github.io/ViewPoint

Discrete JEPA: Learning Discrete Token Representations without Reconstruction

Junyeob Baek, Hosung Lee, Christopher Hoang, Mengye Ren, Sungjin Ahn

机构 * nyu（纽约大学） 纠错

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

Vector Ontologies as an LLM world view extraction method

Kaspar Rothenfusser, Bekk Blando

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

Resilient-native and Intelligent NextG Systems

Mehdi Bennis

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

SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields

Qijing Li, Jingxiang Sun, Liang An, Zhaoqi Su, Hongwen Zhang, Yebin Liu

机构 * Beijing Normal University（北京师范大学） ； Tsinghua University（清华大学） 纠错

专题命中 具身推理 ：robotic(abstract)；分类 cs.CV

Analyzing Transformer Models and Knowledge Distillation Approaches for Image Captioning on Edge AI

Wing Man Casca Kwok, Yip Chiu Tung, Kunal Bhagchandani

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

The Limits of Predicting Agents from Behaviour

Alexis Bellot, Jonathan Richens, Tom Everitt

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

Journal ref ICML 2025

Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames

Sahithya Ravi, Gabriel Sarch, Vibhav Vineet, Andrew D. Wilson, Balasaravanan Thoravi Kumaravel

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Microsoft Research, Redmond WA（微软研究院（红mond, WA）） 纠错

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

Position: Interactive Generative Video as Next-Generation Game Engine

Jiwen Yu, Yiran Qin, Haoxuan Che, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Xihui Liu

机构 * HKU（香港大学） ； HKUST（香港理工大学） ； Kuaishou Technology（快手科技） 纠错

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

Automating Thought of Search: A Journey Towards Soundness and Completeness

Daniel Cao, Michael Katz, Harsha Kokel, Kavitha Srinivas, Shirin Sohrabi

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

Causal Bayesian Networks for Data-driven Safety Analysis of Complex Systems

Roman Gansch, Lina Putze, Tjark Koopmann, Jan Reich, Christian Neurohr

机构 * Robert Bosch GmbH, Corporate Research（罗伯特·博世有限公司，企业研究） ； German Aerospace Center (DLR) e.V., Institute of Systems Engineering for Future Mobility（德国航空航天中心（DLR）协会，未来交通系统工程研究所） ； Fraunhofer Institute for Experimental Software Engineering (IESE)（弗劳恩霍夫实验软件工程研究所） 纠错

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

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving

Chen Shi, Shaoshuai Shi, Kehua Sheng, Bo Zhang, Li Jiang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Voyager Research, Didi Chuxing（Voyager Research，滴滴出行） 纠错

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

DC-Scene: Data-Centric Learning for 3D Scene Understanding

Ting Huang, Zeyu Zhang, Ruicheng Zhang, Yang Zhao

机构 * Shanghai University of Engineering Science（上海工程科学大学） ； The Australian National University（澳大利亚国立大学） ； Sun Yat-sen University（中山大学） ； La Trobe University（拉筹伯大学） 纠错

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

Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?

Zihao Dongfang, Xu Zheng, Ziqiao Weng, Yuanhuiyi Lyu, Danda Pani Paudel, Luc Van Gool, Kailun Yang, Xuming Hu

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

A Light and Smart Wearable Platform with Multimodal Foundation Model for Enhanced Spatial Reasoning in People with Blindness and Low Vision

Alexey Magay, Dhurba Tripathi, Yu Hao, Yi Fang

机构 * Embodied AI and Robotics (AIR) Lab New York University Abu Dhabi（embodied AI 和机器人（AIR）实验室 新 York 大学阿布扎赫德） 纠错

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

Comments Project website and code: https://dktpt44.github.io/LV-GPT/

Leveraging Computation of Expectation Models for Commonsense Affordance Estimation on 3D Scene Graphs

Mario A. V. Saucedo, Nikolaos Stathoulopoulos, Akash Patel, Christoforos Kanellakis, George Nikolakopoulos

机构 * Robotics & AI Team, Department of Computer, Electrical and Space Engineering, Luleå University of Technology（机器人与人工智能团队，计算机、电气与航天工程系，卢勒奥技术大学） 纠错

专题命中 具身推理 ：robotic(abstract)；分类 cs.RO

Comments Accepted at IROS24

3D Vision-Language Gaussian Splatting

Qucheng Peng, Benjamin Planche, Zhongpai Gao, Meng Zheng, Anwesa Choudhuri, Terrence Chen, Chen Chen, Ziyan Wu

机构 * Center for Research in Computer Vision, University of Central Florida（计算机视觉研究中心，佛罗里达大学） 纠错

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

Comments Accepted at ICLR 2025. Main paper + supplementary material

Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding

Yan Wang, Baoxiong Jia, Ziyu Zhu, Siyuan Huang

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Tsinghua University（清华大学） 纠错

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

Comments CVPR 2025

OpenFusion++: An Open-vocabulary Real-time Scene Understanding System

Xiaofeng Jin, Matteo Frosi, Matteo Matteucci

机构 * Politecnico di Milano（米兰理工学院） 纠错

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

Comments 8 pages, 9 figures

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents

Vardhan Dongre, Xiaocheng Yang, Emre Can Acikgoz, Suvodip Dey, Gokhan Tur, Dilek Hakkani-Tür

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments 31 pages, 10 Figures, 25 Tables

CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting

Wei Sun, Yanzhao Zhou, Jianbin Jiao, Yuan Li

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

3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians

Zeming Wei, Junyi Lin, Yang Liu, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin

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

Comments The first large-scale 3D Gaussians Affordance Reasoning Benchmark

InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception

Haijie Li, Yanmin Wu, Jiarui Meng, Qiankun Gao, Zhiyao Zhang, Ronggang Wang, Jian Zhang

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

Comments 14 pages, accepted by CVPR 2025 as poster

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

Veniamin Veselovsky, Berke Argin, Benedikt Stroebl, Chris Wendler, Robert West, James Evans, Thomas L. Griffiths, Arvind Narayanan

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

Vision-Language Embodiment for Monocular Depth Estimation

Jinchang Zhang, Guoyu Lu

专题命中 具身推理 ：robotic(abstract)；分类 cs.CV

IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments

Can Zhang, Gim Hee Lee

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

DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting

Luis Wiedmann, Luca Wiehe, David Rozenberszki

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

Comments To be published in CVPR Workshop on Open-World 3D Scene Understanding with Foundation Models

3D-TAFS: A Training-free Framework for 3D Affordance Segmentation

Meng Chu, Xuan Zhang, Zhedong Zheng, Tat-Seng Chua

专题命中 具身推理 ：robotic(abstract)；分类 cs.RO

Visual Agentic AI for Spatial Reasoning with a Dynamic API

Damiano Marsili, Rohun Agrawal, Yisong Yue, Georgia Gkioxari

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

Comments Project website: https://glab-caltech.github.io/vadar/