Cover Image

DISK: Dynamic Inference SKipping for World Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Naman, Anugunj, Zhang, Gaibo, Singh, Ayushman, Zhang, Yaguang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LAW & ORDER: Adaptive Spatial Weighting for Medical Diffusion and Segmentation
by: Naman, Anugunj, et al.
Published: (2026)

Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling
by: Qi, Han, et al.
Published: (2025)

Dream to Drive with Predictive Individual World Model
by: Gao, Yinfeng, et al.
Published: (2025)

WorldEval: World Model as Real-World Robot Policies Evaluator
by: Li, Yaxuan, et al.
Published: (2025)

ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark
by: Dang, Ronghao, et al.
Published: (2025)

Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression
by: Wang, Lirui, et al.
Published: (2025)

Interactive World Simulator for Robot Policy Training and Evaluation
by: Wang, Yixuan, et al.
Published: (2026)

Being-H0.7: A Latent World-Action Model from Egocentric Videos
by: Luo, Hao, et al.
Published: (2026)

Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model
by: You, Junqi, et al.
Published: (2024)

Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos
by: Zhang, Kaifeng, et al.
Published: (2025)

World Action Models are Zero-shot Policies
by: Ye, Seonghyeon, et al.
Published: (2026)

LUMOS: Language-Conditioned Imitation Learning with World Models
by: Nematollahi, Iman, et al.
Published: (2025)

DiWA: Diffusion Policy Adaptation with World Models
by: Chandra, Akshay L, et al.
Published: (2025)

Learning Massively Multitask World Models for Continuous Control
by: Hansen, Nicklas, et al.
Published: (2025)

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

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

Hierarchical World Models as Visual Whole-Body Humanoid Controllers
by: Hansen, Nicklas, et al.
Published: (2024)

ACT-Bench: Towards Action Controllable World Models for Autonomous Driving
by: Arai, Hidehisa, et al.
Published: (2024)

iVideoGPT: Interactive VideoGPTs are Scalable World Models
by: Wu, Jialong, et al.
Published: (2024)

Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
by: Escoriza, Adrià López, et al.
Published: (2025)

PointVLA: Injecting the 3D World into Vision-Language-Action Models
by: Li, Chengmeng, et al.
Published: (2025)

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
by: Nilaksh, et al.
Published: (2026)

Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects
by: Kreber, Jens U., et al.
Published: (2026)

AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation
by: Zhang, Kaifeng, et al.
Published: (2024)

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
by: Liang, Yichao, et al.
Published: (2025)

Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking
by: Chib, Pranav Singh, et al.
Published: (2024)

PVI: Plug-in Visual Injection for Vision-Language-Action Models
by: Zhang, Zezhou, et al.
Published: (2026)

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
by: Zheng, Xiaoji, et al.
Published: (2025)

TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
by: Lee, Seungjae, et al.
Published: (2025)

Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
by: Zhang, Yanyan, et al.
Published: (2026)

Camera Agnostic Two-Head Network for Ego-Lane Inference
by: Song, Chaehyeon, et al.
Published: (2024)

GIRA: Gaussian Mixture Models for Inference and Robot Autonomy
by: Goel, Kshitij, et al.
Published: (2023)

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

Evaluating Real-World Robot Manipulation Policies in Simulation
by: Li, Xuanlin, et al.
Published: (2024)

HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model
by: Liu, Qi, et al.
Published: (2025)

LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation
by: Zhou, Chenxu, et al.
Published: (2024)

PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics
by: Luan, Xueyu, et al.
Published: (2026)

High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning
by: Schulze, Lennart, et al.
Published: (2023)

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
by: AgiBot-World-Contributors, et al.
Published: (2025)

Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments
by: Shao, Xingyu, et al.
Published: (2026)