English
Related papers

Related papers: GeoWorld: Geometric World Models

200 papers

Backward compatible representation learning enables updated models to integrate seamlessly with existing ones, avoiding to reprocess stored data. Despite recent advances, existing compatibility approaches in Euclidean space neglect the…

Machine Learning · Computer Science 2025-06-09 Ngoc Bui , Menglin Yang , Runjin Chen , Leonardo Neves , Mingxuan Ju , Rex Ying , Neil Shah , Tong Zhao

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

Robotics · Computer Science 2026-03-13 Jin Yang , Ping Wei , Yixin Chen , Nanning Zheng

A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for…

Machine Learning · Computer Science 2026-04-22 Zaishuo Xia , Yukuan Lu , Xinyi Li , Yifan Xu , Yubei Chen

Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods explore multiple paths but are computation-heavy. We address this gap by distilling…

Artificial Intelligence · Computer Science 2026-05-29 Yuyu Liu , Haotian Xu , Yanan He , Sarang Rajendra Patil , Mengjia Xu , Tengfei Ma

World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the…

Machine Learning · Computer Science 2026-02-25 Leonardo F. Toso , Davit Shadunts , Yunyang Lu , Nihal Sharma , Donglin Zhan , Nam H. Nguyen , James Anderson

Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Deshui Miao , Xingsen Huang , Yameng Gu , Xin Li , Haijun Zhang , Ming-Hsuan Yang

World models enable model-based planning through learned latent dynamics, but imagined rollouts become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability reflects two missing…

Artificial Intelligence · Computer Science 2026-05-08 Haoyun Tang , Haodong Cui , Keyao Xu , Kun Wang , Zhandong Mei

Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geography. Existing paradigms rely on either large-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Hari Krishna Gadi , Daniel Matos , Hongyi Luo , Lu Liu , Yongliang Wang , Yanfeng Zhang , Liqiu Meng

Learning low-dimensional numerical representations from symbolic data, e.g., embedding the nodes of a graph into a geometric space, is an important concept in machine learning. While embedding into Euclidean space is common, recent…

Machine Learning · Computer Science 2024-10-10 Thomas Bläsius , Jean-Pierre von der Heydt , Maximilian Katzmann , Nikolai Maas

Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging. This raises a central question: when does a learned representation…

Robotics · Computer Science 2026-05-12 Hoang Nguyen , Xiaohao Xu , Xiaonan Huang

We introduce LivingWorld, an interactive framework for generating 4D worlds with environmental dynamics from a single image. While recent advances in 3D scene generation enable large-scale environment creation, most approaches focus…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Hyeongju Mun , In-Hwan Jin , Sohyeong Kim , Kyeongbo Kong

Humanoid robot loco-manipulation remains constrained by the semantic-physical gap. Current methods face three limitations: Low sample efficiency in reinforcement learning, poor generalization in imitation learning, and physical…

Robotics · Computer Science 2026-01-27 Yutong Shen , Hangxu Liu , Kailin Pei , Ruizhe Xia , Tongtong Feng

Many quantities we are interested in predicting are geometric tensors; we refer to this class of problems as geometric prediction. Attempts to perform geometric prediction in real-world scenarios have been limited to approximating them…

Machine Learning · Computer Science 2020-06-26 Raphael J. L. Townshend , Brent Townshend , Stephan Eismann , Ron O. Dror

Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Jiahao Wang , Luoxin Ye , TaiMing Lu , Junfei Xiao , Jiahan Zhang , Yuxiang Guo , Xijun Liu , Rama Chellappa , Cheng Peng , Alan Yuille , Jieneng Chen

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

Artificial Intelligence · Computer Science 2021-07-02 Lunjun Zhang , Ge Yang , Bradly C. Stadie

Recent studies have demonstrated the potential of hyperbolic geometry for capturing complex patterns from interaction data in recommender systems. In this work, we introduce a novel hyperbolic recommendation model that uses geometrical…

Information Retrieval · Computer Science 2025-08-19 Viacheslav Yusupov , Maxim Rakhuba , Evgeny Frolov

Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy…

World models enable robots to conduct counterfactual reasoning in physical environments by predicting future world states. While conventional approaches often prioritize pixel-level reconstruction of future scenes, such detailed rendering…

Robotics · Computer Science 2025-12-22 Zhiwei Zhang , Hui Zhang , Kaihong Huang , Chenghao Shi , Huimin Lu

A key challenge in artificial intelligence and neuroscience is understanding how neural systems learn representations that capture the underlying dynamics of the world. Most world models represent the transition function with unstructured…

Machine Learning · Computer Science 2026-02-26 William Youngwoo Chung , Calvin Yeung , Hansen Jin Lillemark , Zhuowen Zou , Xiangjian Liu , Mohsen Imani

Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data are scarce. Among existing approaches, methods derived from…

Machine Learning · Computer Science 2026-04-29 Ali Aghababaei-Harandi , Aude Sportisse , Massih-Reza Amini