Imagen de Portada

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gupta, Gunshi, Yadav, Karmesh, Kira, Zsolt, Gal, Yarin, Aljundi, Rahaf
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computer Vision and Pattern Recognition Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
por: Yadav, Karmesh, et al.
Publicado: (2025)

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
por: Gupta, Gunshi, et al.
Publicado: (2024)

MemoNav: Working Memory Model for Visual Navigation
por: Li, Hongxin, et al.
Publicado: (2024)

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
por: Dorovatas, Vaggelis, et al.
Publicado: (2025)

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
por: Kang, Li, et al.
Publicado: (2025)

Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets
por: Coholich, Jeremiah, et al.
Publicado: (2026)

Efficient Few-Shot Continual Learning in Vision-Language Models
por: Panos, Aristeidis, et al.
Publicado: (2025)

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
por: Choi, Wonje, et al.
Publicado: (2024)

HomeRobot: Open-Vocabulary Mobile Manipulation
por: Yenamandra, Sriram, et al.
Publicado: (2023)

Embodied Agents for Efficient Exploration and Smart Scene Description
por: Bigazzi, Roberto, et al.
Publicado: (2023)

Autonomous Embodied Agents: When Robotics Meets Deep Learning Reasoning
por: Bigazzi, Roberto
Publicado: (2025)

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
por: Majumdar, Arjun, et al.
Publicado: (2023)

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
por: Tomilin, Tristan, et al.
Publicado: (2025)

EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling
por: Wang, Boyuan, et al.
Publicado: (2025)

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
por: Xi, Jiajun, et al.
Publicado: (2024)

EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering
por: Cheng, Kai, et al.
Publicado: (2024)

BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
por: Ma, Xiaoyu, et al.
Publicado: (2026)

Neural Brain: A Neuroscience-inspired Framework for Embodied Agents
por: Liu, Jian, et al.
Publicado: (2025)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
por: Liu, Jiahang, et al.
Publicado: (2025)

The Safety Challenge of World Models for Embodied AI Agents: A Review
por: Baraldi, Lorenzo, et al.
Publicado: (2025)

Spot the Difference: A Novel Task for Embodied Agents in Changing Environments
por: Landi, Federico, et al.
Publicado: (2022)

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
por: Wang, Le, et al.
Publicado: (2025)

Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent
por: Yu, Che Rin, et al.
Publicado: (2025)

Your Robot Will Feel You Now: Empathy in Robots and Embodied Agents
por: Lim, Angelica, et al.
Publicado: (2026)

Evaluating the Impact of Post-Training Quantization on Reliable VQA with Multimodal LLMs
por: Kurz, Paul Jonas, et al.
Publicado: (2026)

Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
por: Zadaianchuk, Andrii, et al.
Publicado: (2026)

SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
por: Chen, Ziyi, et al.
Publicado: (2025)

Dejavu: Towards Experience Feedback Learning for Embodied Intelligence
por: Wu, Shaokai, et al.
Publicado: (2025)

Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models
por: Lei, Zixing, et al.
Publicado: (2026)

IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
por: Chen, Yandu, et al.
Publicado: (2025)

EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI
por: Chang, Jianlei, et al.
Publicado: (2025)

EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device
por: Chhablani, Gunjan, et al.
Publicado: (2025)

Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model
por: Xu, Wenjiang, et al.
Publicado: (2025)

The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning
por: Senanayake, Ransalu
Publicado: (2024)

Building Cooperative Embodied Agents Modularly with Large Language Models
por: Zhang, Hongxin, et al.
Publicado: (2023)

Embodied Navigation at the Art Gallery
por: Bigazzi, Roberto, et al.
Publicado: (2022)

Ego: Embedding-Guided Personalization of Vision-Language Models
por: Seifi, Soroush, et al.
Publicado: (2026)

Embodied Uncertainty-Aware Object Segmentation
por: Fang, Xiaolin, et al.
Publicado: (2024)

Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
por: Panos, Aristeidis, et al.
Publicado: (2024)

MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
por: Huang, Chengyue, et al.
Publicado: (2025)