ICLR 2025 Past Other
ICLR 2025 Workshop on World Models: Understanding, Modelling and Scaling
ICLR 2025 Workshop World Models
- Submission deadline
- Feb 27, 2025, 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 (63)
Fetched from OpenReview (v2) on 2026-06-10.
-
A Proposal for Networks Capable of Continual Learning
-
A Virtual Reality-Integrated System for Behavioral Analysis in Neurological Decline
-
Accelerating Goal-Conditioned RL Algorithms and Research
-
Accelerating Model-Based Reinforcement Learning with State-Space World Models
-
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
-
ACT-Bench: Towards Action Controllable World Models for Autonomous Driving
-
Adapting a World Model for Trajectory Following in a 3D Game
-
BEYOND SINGLE-STEP: MULTI-FRAME ACTION- CONDITIONED VIDEO GENERATION FOR REINFORCE- MENT LEARNING ENVIRONMENTS
-
BiD: Behavioral Agents in Dynamic Auctions
-
COMPARATIVE STUDY OF WORLD MODELS, NVAE-BASED HIERARCHICAL MODELS, AND NOISYNET-AUGMENTED MODELS IN CARRACING-V2
-
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
-
DIALOGUES BETWEEN ADAM AND EVE: EXPLORATION OF UNKNOWN CIVILIZATION LANGUAGE BY LLM
-
Distribution Recovery in Compact Diffusion World Models via Conditioned Frame Interpolation
-
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
-
Effectively Designing 2-Dimensional Sequence Models for Multivariate Time Series
-
Emergent Stack Representations in Modeling Counter Languages Using Transformers
-
Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations
-
From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
-
Generalist World Model Pre-Training for Efficient Reinforcement Learning
-
Generating Symbolic World Models via Test-time Scaling of Large Language Models
-
GOLLuM: Gaussian Process Optimized LLMs — Reframing LLM Finetuning through Bayesian Optimization
-
HEP-JEPA: A foundation model for collider physics
-
HuWo: Building Physical Interaction World Models for Humanoid Robot Locomotion
-
Improving Transformer World Models for Data-Efficient RL
-
Improving World Models using Supervision with Co-Evolving Linear Probes
-
Knowledge Graphs as World Models for Semantic Material-Aware Obstacle Handling in Autonomous Vehicles
-
Latent Action Learning Requires Supervision in the Presence of Distractors
-
Latent Representation Encoding and Multimodal Biomarkers for Post-Stroke Speech Assessment
-
LEARNING FROM LESS: SINDY SURROGATES IN RL
-
Masked Generative Priors Improve World Models Sequence Modelling Capabilities
-
Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs
-
Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity
-
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
-
Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning
-
MS-SSM: A Multi-Scale State Space Model for Enhanced Sequence Modeling
-
Newton - A Small Benchmark for Interactive Foundation World Models
-
Object-Centric Latent Action Learning
-
Object-Centric Representations Generalize Better Compositionally with Less Compute
-
Object-Centric World Model for Language-Guided Manipulation
-
PINT: Physics-Informed Neural Time Series Models with Applications to Long-term Inference on WeatherBench 2m-Temperature Data
-
Pre-Trained Video Generative Models as World Simulators
-
Programmatic Video Prediction Using Large Language Models
-
Pushing the Limit of Sample-Efficient Offline Reinforcement Learning
-
RADI: LLMs as World Models for Robotic Action Decomposition and Imagination
-
Reconstructing Dynamics from Steady Spatial Patterns with Partial Observations
-
Recurrent world model with tokenized latent states
-
Revisiting the Othello World Model Hypothesis
-
Reward-free World Models for Online Imitation Learning
-
Scalable Humanoid Whole-Body Control via Differentiable Neural Network Dynamics
-
Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
-
Scaling Laws for Pre-training Agents and World Models
-
SEAL: SEmantic-Augmented Imitation Learning via Language Model
-
Stress-Testing Offline Reward-Free Reinforcement Learning: A Case for Planning with Latent Dynamics Models
-
Temporal Difference Flows
-
Text2World: Benchmarking Large Language Models for Symbolic World Model Generation
-
Trajectory World Models for Heterogeneous Environments
-
Transformers Use Causal World Models in Maze-Solving Tasks
-
TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
-
Unifying Causal and Object-centric Representation Learning allows Causal Composition
-
Unifying Unsupervised and Offline RL for Fast Adaptation Using World Models
-
Utilizing World Models for Adaptively Covariate Acquisition Under Limited Budget for Causal Decision Making Problem
-
When do neural networks learn world models?
-
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning