Cover Image

World2Act: Latent Action Post-Training from World Model Dynamics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vuong, An Dinh, Van Vo, Tuan, Sohail, Abdullah, Ding, Haoran, Ma, Liang, Liang, Xiaodan, Duan, Anqing, Laptev, Ivan, Reid, Ian
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Choose What to Observe: Task-Aware Semantic-Geometric Representations for Visuomotor Policy
by: Ding, Haoran, et al.
Published: (2026)

Latent Action Pretraining Through World Modeling
by: Tharwat, Bahey, et al.
Published: (2025)

Action Tokenizer Matters in In-Context Imitation Learning
by: Vuong, An Dinh, et al.
Published: (2025)

GLaD: Geometric Latent Distillation for Vision-Language-Action Models
by: Guo, Minghao, et al.
Published: (2025)

Improving Robotic Manipulation with Efficient Geometry-Aware Vision Encoder
by: Vuong, An Dinh, et al.
Published: (2025)

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling
by: Cao, Meng, et al.
Published: (2025)

Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos
by: Cao, Meng, et al.
Published: (2026)

3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning
by: Chen, Chenyuan, et al.
Published: (2025)

ActionSink: Toward Precise Robot Manipulation with Dynamic Integration of Action Flow
by: Guo, Shanshan, et al.
Published: (2025)

Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
by: Gao, Jiaxuan, et al.
Published: (2026)

NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
by: Huang, Wen, et al.
Published: (2026)

GeoWorld: Geometric World Models
by: Zhang, Zeyu, et al.
Published: (2026)

Pre-Trained Video Generative Models as World Simulators
by: He, Haoran, et al.
Published: (2025)

RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
by: Han, Mingfei, et al.
Published: (2024)

Olaf-World: Orienting Latent Actions for Video World Modeling
by: Jiang, Yuxin, et al.
Published: (2026)

AdaWorld: Learning Adaptable World Models with Latent Actions
by: Gao, Shenyuan, et al.
Published: (2025)

Factored Latent Action World Models
by: Wang, Zizhao, et al.
Published: (2026)

Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference
by: Ding, Haoran, et al.
Published: (2025)

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
by: Jiang, Anqing, et al.
Published: (2025)

Motus: A Unified Latent Action World Model
by: Bi, Hongzhe, et al.
Published: (2025)

Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos
by: Han, Mingfei, et al.
Published: (2026)

Learning Latent Action World Models In The Wild
by: Garrido, Quentin, et al.
Published: (2026)

Self-Improving World Modelling with Latent Actions
by: Qiu, Yifu, et al.
Published: (2026)

Co-Evolving Latent Action World Models
by: Wang, Yucen, et al.
Published: (2025)

SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery
by: Cao, Meng, et al.
Published: (2025)

Counting to Four is still a Chore for VLMs
by: Anh, Duy Le Dinh, et al.
Published: (2026)

Language-driven Grasp Detection with Mask-guided Attention
by: Van Vo, Tuan, et al.
Published: (2024)

Strain Effect on Rashba Splitting and Phonon Scattering to Improve Thermoelectric Performance of 2D Heterobilayer MoTe$_{2}$/PtS$_{2}$
by: Van Thanh, Vuong, et al.
Published: (2025)

DiLA: Disentangled Latent Action World Models
by: Zhang, Tianqiu, et al.
Published: (2026)

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

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
by: Sun, Xiaoquan, et al.
Published: (2026)

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
by: Chen, Yi, et al.
Published: (2026)

Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
by: Wang, Linbo, et al.
Published: (2026)

Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
by: Liu, Yang, et al.
Published: (2024)

Surfer: Progressive Reasoning with World Models for Robotic Manipulation
by: Ren, Pengzhen, et al.
Published: (2023)

Effects of dynamical dielectric screening on the excitonic spectrum of monolayer semiconductors
by: Van Tuan, Dinh, et al.
Published: (2024)

Component exchange theory of trions
by: Van Tuan, Dinh, et al.
Published: (2024)

Landau-level composition of bound exciton states in magnetic field
by: Van Tuan, Dinh, et al.
Published: (2025)

PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
by: Zhang, Kaidong, et al.
Published: (2024)

Learning to Act Robustly with View-Invariant Latent Actions
by: Jeong, Youngjoon, et al.
Published: (2026)