Imagen de Portada

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Pingyue, Huang, Zihan, Wang, Yue, Zhang, Jieyu, Xue, Letian, Wang, Zihan, Wang, Qineng, Chandrasegaran, Keshigeyan, Zhang, Ruohan, Choi, Yejin, Krishna, Ranjay, Wu, Jiajun, Fei-Fei, Li, Li, Manling
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MindCube: Spatial Mental Modeling from Limited Views
por: Wang, Qineng, et al.
Publicado: (2025)

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
por: Wang, Kangrui, et al.
Publicado: (2025)

RAGEN-2: Reasoning Collapse in Agentic RL
por: Wang, Zihan, et al.
Publicado: (2026)

T*: Re-thinking Temporal Search for Long-Form Video Understanding
por: Ye, Jinhui, et al.
Publicado: (2025)

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
por: Wang, Zihan, et al.
Publicado: (2025)

Planning with the Views via Scene Self-Exploration
por: Wang, Kangrui, et al.
Publicado: (2026)

HourVideo: 1-Hour Video-Language Understanding
por: Chandrasegaran, Keshigeyan, et al.
Publicado: (2024)

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
por: Wang, Qineng, et al.
Publicado: (2025)

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
por: Hong, Yining, et al.
Publicado: (2026)

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
por: Hong, Yining, et al.
Publicado: (2026)

GPIC: A Giant Permissive Image Corpus for Visual Generation
por: Chandrasegaran, Keshigeyan, et al.
Publicado: (2026)

TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction
por: Jiang, Yunfan, et al.
Publicado: (2024)

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
por: Li, Manling, et al.
Publicado: (2024)

Model Inversion Robustness: Can Transfer Learning Help?
por: Ho, Sy-Tuyen, et al.
Publicado: (2024)

Iterated Learning Improves Compositionality in Large Vision-Language Models
por: Zheng, Chenhao, et al.
Publicado: (2024)

Exploring Diffusion Transformer Designs via Grafting
por: Chandrasegaran, Keshigeyan, et al.
Publicado: (2025)

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
por: Dharmarajan, Karthik, et al.
Publicado: (2025)

I Can Tell What I am Doing: Toward Real-World Natural Language Grounding of Robot Experiences
por: Wang, Zihan, et al.
Publicado: (2024)

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations
por: Li, Linjie, et al.
Publicado: (2025)

ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
por: Huang, Wenlong, et al.
Publicado: (2024)

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
por: Gao, Ziqi, et al.
Publicado: (2024)

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
por: Ma, Zixian, et al.
Publicado: (2024)

You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
por: Yang, Yinuo, et al.
Publicado: (2026)

Offline Training of Language Model Agents with Functions as Learnable Weights
por: Zhang, Shaokun, et al.
Publicado: (2024)

Can Large Language Models Reinvent Foundational Algorithms?
por: Zhao, Jian, et al.
Publicado: (2026)

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
por: Zhao, Hongjue, et al.
Publicado: (2026)

A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
por: Liu, Licheng, et al.
Publicado: (2025)

UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation
por: Tang, Yihe, et al.
Publicado: (2025)

Non-unique decompositions of mixed states and deterministic energy transfers
por: Wang, Zihan, et al.
Publicado: (2025)

VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge
por: Li, Zihan, et al.
Publicado: (2024)

AirShot: Efficient Few-Shot Detection for Autonomous Exploration
por: Wang, Zihan, et al.
Publicado: (2024)

Automated Creation of Digital Cousins for Robust Policy Learning
por: Dai, Tianyuan, et al.
Publicado: (2024)

Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models
por: Wang, Zihan, et al.
Publicado: (2025)

Order Matters: Rethinking Prompt Construction in In-Context Learning
por: Li, Warren, et al.
Publicado: (2025)

DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation
por: Wang, Chen, et al.
Publicado: (2024)

A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
por: Abdollahzadeh, Milad, et al.
Publicado: (2023)

IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction
por: Wang, Yingke, et al.
Publicado: (2026)

EMCompress: Video-LLMs with Endomorphic Multimodal Compression
por: Fan, Zheyu, et al.
Publicado: (2025)

Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models
por: Ye, Ruimeng, et al.
Publicado: (2025)

Artificial Entanglement in the Fine-Tuning of Large Language Models
por: Chen, Min, et al.
Publicado: (2026)