Imagen de Portada

LIMT: Language-Informed Multi-Task Visual World Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Aljalbout, Elie, Sotirakis, Nikolaos, van der Smagt, Patrick, Karl, Maximilian, Chen, Nutan
Formato:	Preprint
Publicado:	2024
Materias:	Robotics Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer
por: Aljalbout, Elie, et al.
Publicado: (2023)

Guided Decoding for Robot On-line Motion Generation and Adaption
por: Chen, Nutan, et al.
Publicado: (2024)

The Shortcomings of Force-from-Motion in Robot Learning
por: Aljalbout, Elie, et al.
Publicado: (2024)

FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
por: Alles, Marvin, et al.
Publicado: (2025)

Multi-Task Reinforcement Learning for Quadrotors
por: Xing, Jiaxu, et al.
Publicado: (2024)

Student-Informed Teacher Training
por: Messikommer, Nico, et al.
Publicado: (2024)

Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models
por: Zhang, Xingyuan, et al.
Publicado: (2024)

Accelerating Model-Based Reinforcement Learning with State-Space World Models
por: Krinner, Maria, et al.
Publicado: (2025)

Cross-Modal Visuo-Tactile Object Perception
por: Dutta, Anirvan, et al.
Publicado: (2026)

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
por: Alles, Marvin, et al.
Publicado: (2024)

PWM: Policy Learning with Multi-Task World Models
por: Georgiev, Ignat, et al.
Publicado: (2024)

A Distributed Gaussian Process Model for Multi-Robot Mapping
por: Nabarro, Seth, et al.
Publicado: (2026)

Latent Action World Models for Control with Unlabeled Trajectories
por: Alles, Marvin, et al.
Publicado: (2025)

World Model-based Perception for Visual Legged Locomotion
por: Lai, Hang, et al.
Publicado: (2024)

Modeling the Real World with High-Density Visual Particle Dynamics
por: Whitney, William F., et al.
Publicado: (2024)

Bird's Eye View Based Pretrained World model for Visual Navigation
por: Lekkala, Kiran, et al.
Publicado: (2023)

Accelerating Real-World Overtaking in F1TENTH Racing Employing Reinforcement Learning Methods
por: Steiner, Emily, et al.
Publicado: (2025)

Language-Conditioned Representations and Mixture-of-Experts Policy for Robust Multi-Task Robotic Manipulation
por: Zhang, Xiucheng, et al.
Publicado: (2025)

RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models
por: Li, Jingyao, et al.
Publicado: (2024)

Latent Matters: Learning Deep State-Space Models
por: Klushyn, Alexej, et al.
Publicado: (2026)

MEM: Multi-Scale Embodied Memory for Vision Language Action Models
por: Torne, Marcel, et al.
Publicado: (2026)

$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
por: Intelligence, Physical, et al.
Publicado: (2025)

Autonomous Reality Modelling for Cultural Heritage Sites employing cooperative quadrupedal robots and unmanned aerial vehicles
por: Giakoumidis, Nikolaos, et al.
Publicado: (2024)

M3PO: Massively Multi-Task Model-Based Policy Optimization
por: Narendra, Aditya, et al.
Publicado: (2025)

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
por: Francis-Meretzki, Shelly, et al.
Publicado: (2026)

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
por: Zhang, Zhilong, et al.
Publicado: (2026)

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents
por: Kuzmenko, Dmytro, et al.
Publicado: (2025)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
por: Li, Runze, et al.
Publicado: (2026)

Active Fine-Tuning of Multi-Task Policies
por: Bagatella, Marco, et al.
Publicado: (2024)

PhysVarMix: Physics-Informed Variational Mixture Model for Multi-Modal Trajectory Prediction
por: Li, Haichuan, et al.
Publicado: (2025)

World-Task Factorization for Robot Learning
por: Sebastián, Eduardo, et al.
Publicado: (2026)

MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
por: Huang, Suning, et al.
Publicado: (2024)

Learning Humanoid Locomotion with World Model Reconstruction
por: Sun, Wandong, et al.
Publicado: (2025)

Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
por: Vainshtein, Ron, et al.
Publicado: (2025)

Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
por: Feng, Jinyuan, et al.
Publicado: (2024)

Sequential Model for Predicting Patient Adherence in Subcutaneous Immunotherapy for Allergic Rhinitis
por: Li, Yin, et al.
Publicado: (2024)

FAST: Efficient Action Tokenization for Vision-Language-Action Models
por: Pertsch, Karl, et al.
Publicado: (2025)

Grounding Language Models in Autonomous Loco-manipulation Tasks
por: Wang, Jin, et al.
Publicado: (2024)

Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust
por: Hancock, Asher J., et al.
Publicado: (2024)

Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
por: Hao, Chenjie, et al.
Publicado: (2025)