ICLR 2026 Past Other
ICLR 2026 the 2nd Workshop on World Models: Understanding, Modelling and Scaling
ICLR 2026 Workshop World Models
- Submission deadline
- Feb 8, 2026, 11:59 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (94)
Fetched from OpenReview (v2) on 2026-06-10.
-
[Tiny Paper] Safe Streaming Flow Planning by Aligning Generation with Execution
-
[Tiny Paper] GEST-Engine: Controllable Multi-Actor Video Synthesis with Perfect Spatiotemporal Annotations
-
[Tiny Paper] Integrating Simulation and Chain-of-thought Reasoning in Multimodal-Language Models For Physical Reasoning
-
[Tiny Paper] Intrinsic-Energy Joint Embedding Predictive Architectures Induce Quasimetric Spaces
-
[Tiny Paper] Modular Training-Free Construction of Executable 3D Worlds from Narrative Text
-
[Tiny Paper] Probabilistic Dreaming for World Models
-
[Tiny Paper] Shortcut World Models: Learning to Leap, Not Step
-
[TINY PAPER] Temporal Reversal Asymmetry: A Physics-Inspired Metric for Evaluating World Models
-
[Tiny Paper] Toward Pixel-Grounded World Models for Powered Descent: A Rocket Landing Benchmark and Expert Baseline
-
A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
-
A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
-
Action Shapley: A training data selection metric for Training World Models for Reinforcement Learning
-
Active World-Model with 4D-informed Re- trieval for Exploration and Awareness
-
Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
-
BlockMamba: Efficient Scalable Structured Sparsity for Mamba
-
Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
-
CausalPhysics: Unifying Semantic Reasoning, Physical Dynamics, and Counterfactual Simulation in World Models
-
CausalSliders: Graph-Guided LoRA Interventions for Causally Consistent Image Editing
-
CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
-
Cognitive Digital Twin Framework: Modeling and Real-Time Decision Making
-
Coherence‑Validated Causal World Models for Multi‑Scale Alzheimer’s Disease Progression and Pharmacologic Reversal
-
Compositional Planning with Jumpy World Models
-
Computer-Using World Model
-
Consistent Video World Model With Geometry-Aware Rotary Position Embedding
-
Cross-View World Models
-
Ctrl-World: A Controllable Generative World Model for Robot Manipulation
-
DexSIM: Real-time Dexterous Simulation with Unified Causal Video Diffusion
-
Do LLMs Build Spatial World Models? Evidence from Grid-World Maze Tasks
-
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction [Tiny Paper]
-
Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
-
EGO-FLIGHT: Egocentric Grounding of Order for Frame-Level Inference in General Human Timelines
-
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
-
Environment Maps: Structured Environmental Representations for Long-Horizon Agents
-
Evidential Latent World Models for Safe Model-based Reinforcement Learning
-
EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
-
FluIDWorld: Fluid-like Interactive Dynamics for 4D Worlds
-
GridWM-Judge: Evaluating Vision-Language Model Judges in Grid Worlds via World Model Deficits
-
Grounding Generated Videos in Feasible Plans via World Models
-
H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model
-
Hierarchical Latent Action Model
-
Hierarchical World Models for Strategic AI Agents: Bridging Simulation and Reality through Multi-Fidelity Learning
-
Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
-
Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
-
LaMo: A Latent Motion World Model for Long-Horizon Prediction
-
Latent Imagination Thinking: Beyond Recursive Models for Reasoning
-
LatentGS: Probabilistic Densification for Efficient, Compact, and Faster 3D Gaussian Splatting
-
Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning
-
Learning Navigable World Models via Latent Energy Shaping
-
Lifting Ego World Models for Planning and Control
-
Mnemo: Policy Learning Accelerated by Experience
-
Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning
-
Model Space Reasoning as Search in Feedback Space for Planning Domain Generation
-
Model-Based Meta-Learning for Algorithm Discovery
-
Motion Attribution for Video Generation
-
MULTI-COMPONENT OUTCOME PREDICTION FOR ENTERPRISE ROUTING VIA HIERARCHICAL CREDIT ASSIGNMENT
-
Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning
-
Neural Computers
-
Next Embedding Prediction Makes World Models Stronger
-
Parallel Stochastic Gradient-Based Planning for World Models
-
Physical Informed Driving World Models
-
PhysLang: a Small Diagnostic Framework for Language-Grounded World Modeling
-
Planning with Unified Multimodal Models
-
PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
-
PREDICTING CAMERA POSE FROM PERSPECTIVE DESCRIPTIONS FOR SPATIAL REASONING
-
ProgressLM: Towards Progress Reasoning in Vision-Language Models
-
Reinforcement Learning with World Models for Optimizing Alzheimer’s Disease Treatment Timing and Dosing
-
Rethinking Video Generation Model for the Embodied World
-
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
-
RigidBench: Evaluating Rigid-Body Physics in Video Generation Models
-
Robustness in the Face of Partial Identifiability in Reward Learning Problems
-
Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation
-
Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game
-
Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
-
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models
-
Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
-
Spiking Neural Networks for Continuous Control: Neuromorphic Reinforcement Learning in Conventional Computing
-
stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation [Tiny Paper]
-
Structure from Diffusion: Taming Video Diffusion Models for Camera Pose Estimation in Dynamic Videos
-
the Mouth is Not the Brain: Bridging Energy-Based World Models and Language Generation
-
Toward World Models for Epidemiology
-
Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
-
Tree of Options: Temporally Extended World Modeling, Planning, and Execution with Large Language Models
-
Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
-
Understanding Early Collapse in Predictive World-Model Pretraining
-
VFMF: Dense Forecasting by Generating Foundation Model Features
-
VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
-
Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models
-
WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotics
-
What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
-
What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
-
World Action Models are Zero-shot Policies
-
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
-
World Models as Execution Simulators for Automated Program Repair
-
World-Gymnast: Training Robots with Reinforcement Learning in a World Model