Image de couverture de livre

PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Haoyang, You, Yang, Su, Hao, Guibas, Leonidas
Format:	Preprint
Publié:	2026
Sujets:	Robotics Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MemCtrl: Using MLLMs as Active Memory Controllers on Embodied Agents
par: Dorbala, Vishnu Sashank, et autres
Publié: (2026)

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
par: Hong, Yining, et autres
Publié: (2026)

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
par: Zhang, Lingfeng, et autres
Publié: (2025)

Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools
par: You, Yang, et autres
Publié: (2023)

BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
par: Ma, Xiaoyu, et autres
Publié: (2026)

MemER: Scaling Up Memory for Robot Control via Experience Retrieval
par: Sridhar, Ajay, et autres
Publié: (2025)

Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition
par: Yue, Bo, et autres
Publié: (2025)

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
par: Yuan, Yifu, et autres
Publié: (2025)

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
par: Hong, Yining, et autres
Publié: (2026)

RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems
par: Lei, Mingcong, et autres
Publié: (2025)

Human-centered In-building Embodied Delivery Benchmark
par: Xu, Zhuoqun, et autres
Publié: (2024)

Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
par: Xie, Quanting, et autres
Publié: (2024)

PhysInOne: Visual Physics Learning and Reasoning in One Suite
par: Zhou, Siyuan, et autres
Publié: (2026)

Robot Learning from a Physical World Model
par: Mao, Jiageng, et autres
Publié: (2025)

Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
par: Yang, Siyuan, et autres
Publié: (2025)

Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
par: Tang, Peijun, et autres
Publié: (2025)

HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering
par: Li, Ji, et autres
Publié: (2026)

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
par: Zhao, Jianchao, et autres
Publié: (2026)

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
par: Yang, Yuncong, et autres
Publié: (2025)

Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training
par: Liu, Yi, et autres
Publié: (2025)

PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
par: Chang, Matthew, et autres
Publié: (2024)

Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation
par: Wen, Congcong, et autres
Publié: (2025)

KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
par: Wang, Zixuan, et autres
Publié: (2024)

Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents
par: Kim, Byeonghwi, et autres
Publié: (2023)

PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving
par: Zhao, Zhipeng, et autres
Publié: (2024)

Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation
par: Bai, Qianqian, et autres
Publié: (2025)

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
par: Kim, Dongyoung, et autres
Publié: (2025)

SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
par: Sato, Makoto, et autres
Publié: (2026)

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
par: Yang, Zebin, et autres
Publié: (2026)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
par: Liu, Jiahang, et autres
Publié: (2025)

NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
par: Cui, Tiehan, et autres
Publié: (2026)

PEPA: a Persistently Autonomous Embodied Agent with Personalities
par: Liu, Kaige, et autres
Publié: (2026)

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
par: NVIDIA, et autres
Publié: (2025)

Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering
par: Ginting, Muhammad Fadhil, et autres
Publié: (2025)

EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation
par: Dong, Zibin, et autres
Publié: (2025)

PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos
par: Jiang, Hanxiao, et autres
Publié: (2025)

Towards High-Consistency Embodied World Model with Multi-View Trajectory Videos
par: Su, Taiyi, et autres
Publié: (2025)

Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
par: Zhang, Yi, et autres
Publié: (2026)

Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
par: Ye, Weirui, et autres
Publié: (2023)

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
par: Gao, Chen, et autres
Publié: (2024)