Task structure is identifiable across time steps and task-relevant representations are identifiable within steps in a nonparametric setting under sparsity regularization.
super hub Canonical reference
World Models
Canonical reference. 88% of citing Pith papers cite this work as background.
141
Pith papers citing it
Background
88% of classified citations
abstract
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back into the actual environment. An interactive version of this paper is available at https://worldmodels.github.io/
hub tools
citation-role summary
background 36
method 3
other 1
citation-polarity summary
claims ledger
- abstract We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back into the actual environment. An interactive version of this paper is
authors
co-cited works
representative citing papers
EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
AIQI is the first model-free universal AI agent proven asymptotically ε-optimal in general RL by inducing over distributional Q-functions instead of policies or environments.
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
Demo-JEPA enables one-shot cross-embodiment imitation by mapping visual demonstrations to shared latent future trajectories that serve as subgoals for the target agent's own forward dynamics planning.
Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
Pinductor leverages language-model priors to learn POMDP world models from limited trajectories, matching privileged-access methods in performance and exceeding tabular baselines in sample efficiency.
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
VHYDRO is a support-safe variational hybrid filter that jointly recovers continuous latent states, discrete contact modes, and sparse port-Hamiltonian laws per regime while preventing loss of feasible transitions.
KnotBench benchmark shows state-of-the-art VLMs perform near random on diagrammatic knot reasoning tasks and lack ability to simulate structural moves.
ACWM-Phys is a controllable simulator benchmark with in- and out-of-distribution protocols for evaluating action-conditioned world models across rigid, kinematic, deformable, and particle dynamics.
SYNCR benchmark shows leading MLLMs reach only 52.5% average accuracy on cross-video reasoning tasks against an 89.5% human baseline, with major weaknesses in physical and spatial reasoning.
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
VPSD-RL discovers exact and approximate value-preserving Lie-group operators in continuous RL to stabilize learning via transition augmentation and consistency regularization.
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
Non-monotone triangular SCMs with mechanism-wise invertibility and context-independent inverse transport are equivalent to exogenous isomorphism and achieve complete counterfactual identifiability, with supporting experiments on synthetic data and MuJoCo tasks.
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
The paper unifies emerging graph-based world models under a new paradigm and proposes a taxonomy organized by spatial, physical, and logical relational inductive biases.
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
GTASA supplies annotated multi-actor videos with exact 3D spatial and temporal ground truth that outperforms neural video generators in physical and semantic validity while enabling new probes of video encoders.
EgoTL provides a new egocentric dataset with think-aloud chains and metric labels that benchmarks VLMs on long-horizon tasks and improves their planning, reasoning, and spatial grounding after finetuning.
MotionScape is a large-scale UAV video dataset with highly dynamic 6-DoF motions, geometric trajectories, and semantic annotations to train world models that better simulate complex 3D dynamics under large viewpoint changes.
citing papers explorer
-
From Generalist to Specialist Representation
Task structure is identifiable across time steps and task-relevant representations are identifiable within steps in a nonparametric setting under sparsity regularization.
-
Learning POMDP World Models from Observations with Language-Model Priors
Pinductor leverages language-model priors to learn POMDP world models from limited trajectories, matching privileged-access methods in performance and exceeding tabular baselines in sample efficiency.
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
-
Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
-
Operator-Guided Invariance Learning for Continuous Reinforcement Learning
VPSD-RL discovers exact and approximate value-preserving Lie-group operators in continuous RL to stabilize learning via transition augmentation and consistency regularization.
-
Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal models
Non-monotone triangular SCMs with mechanism-wise invertibility and context-independent inverse transport are equivalent to exogenous isomorphism and achieve complete counterfactual identifiability, with supporting experiments on synthetic data and MuJoCo tasks.
-
Joint Embedding Variational Bayes
VJE is a new variational non-contrastive SSL method that models target embeddings with a directional-radial Student-t distribution to enable structured uncertainty estimation directly in the learned representation space.
-
Neural Neural Scaling Laws
NeuNeu, a neural network trained on HuggingFace checkpoints, predicts language model accuracy on 66 downstream tasks at 1.99% MAE by extrapolating trajectories, outperforming logistic scaling laws by 44% and generalizing zero-shot to new models and tasks.
-
Mastering Atari with Discrete World Models
DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.
-
Dream to Control: Learning Behaviors by Latent Imagination
Dreamer learns to control from images by imagining and optimizing behaviors in a learned latent world model, outperforming prior methods on 20 visual tasks in data efficiency and final performance.
-
Learning the Arrow of Time
Introduces a learned arrow of time in MDPs that aligns with the Jordan-Kinderlehrer-Otto notion for stochastic processes and enables practical RL utilities like reachability and side-effect detection.
-
Exploring Model-based Planning with Policy Networks
POPLIN combines policy networks with model-predictive planning by optimizing either action sequences or policy parameters, yielding 3x better sample efficiency than PETS, TD3 and SAC on MuJoCo locomotion tasks.
-
Neural Point-Forms
Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.
-
PriorZero: Bridging Language Priors and World Models for Decision Making
PriorZero uses root-only LLM prior injection in MCTS and alternating world-model training with LLM fine-tuning to raise exploration efficiency and final performance on Jericho text games and BabyAI gridworlds.
-
MolWorld: Molecule World Models for Actionable Molecular Optimization
MolWorld expands a molecule-transfer graph using a world model to discover high-property molecules that maintain strong structural connectivity to known compounds for actionable optimization.
-
Predictive but Not Plannable: RC-aux for Latent World Models
RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
-
On Training in Imagination
The work derives the optimal ratio of dynamics-to-reward samples that minimizes a bound on return error and characterizes the tradeoff between noisy but cheap rewards versus accurate but expensive ones in imagination-based policy optimization.
-
Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination
Dream-MPC refines policy-generated trajectories by gradient ascent in a latent world model with uncertainty regularization and temporal amortization, improving base policy performance and beating gradient-free MPC on 24 continuous control tasks.
-
TRAP: Tail-aware Ranking Attack for World-Model Planning
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on clean inputs.
-
Data-Driven Open-Loop Simulation for Digital-Twin Operator Decision Support in Wastewater Treatment
CCSS-RS achieves RMSE 0.696 and CRPS 0.349 at 1000-step horizons on a large public WWTP benchmark with 43% missingness, outperforming Neural CDE baselines by 40-46% in RMSE.
-
Learning Ad Hoc Network Dynamics via Graph-Structured World Models
G-RSSM learns per-node dynamics in wireless ad hoc networks via graph attention and trains clustering policies through imagined rollouts, generalizing from N=50 training to larger networks.
-
GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control
GIRL reduces latent rollout drift by 38-61% versus DreamerV3 in MBRL by grounding transitions with DINOv2 embeddings and using an information-theoretic adaptive bottleneck, yielding better long-horizon returns on control benchmarks.
-
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
Dreamer-CDP achieves reconstruction-free world modeling via a JEPA-style predictor on continuous deterministic representations and matches Dreamer's performance on Crafter.
-
Co-Evolving Latent Action World Models
CoLA-World jointly trains latent action models and world models with a warm-up phase to achieve co-evolution, matching or exceeding prior two-stage methods in video simulation quality and visual planning performance.
-
Vidar: Embodied Video Diffusion Model for Generalist Manipulation
Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data.
-
Physically Interpretable World Models via Weakly Supervised Representation Learning
PIWM aligns latent states in image-based world models with physical variables and constrains their dynamics to known equations via weak distribution supervision, yielding accurate long-horizon predictions and parameter recovery on Cart Pole, Lunar Lander, and Donkey Car.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
A two-stage framework learns a world graph of pivotal states task-agnostically via joint training of a latent model and curiosity-driven policy, then uses the graph to accelerate hierarchical RL on maze tasks.
-
ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data
CMWM is a recurrent latent world model for forecasting patient trajectories like annual eGFR in CKD, reporting 7.28% lower MAE than a tuned GPT-5.5 baseline on a 2232-patient cohort with gains from dialogue data.
-
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
-
PROWL: Prioritized Regret-Driven Optimization for World Model Learning
PROWL introduces a KL-constrained adversarial curriculum and prioritized adversarial trajectory buffer to actively discover and correct rare failure modes in action-conditioned video world models.
-
Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari
Transformer world models on Atari exhibit game-specific scaling regimes, but joint training on 26 environments produces consistent monotonic gains that improve downstream control policies to a median normalized score of 0.770.
-
FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
FAAST performs test-time supervised adaptation by analytically deriving fast weights from examples in one forward pass, matching backprop performance with over 90% less adaptation time and up to 95% memory savings versus memory-based methods.
-
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
SPLICE couples JEPA-based latent diffusion with adaptive conformal inference to deliver accurate time-series inpainting with 93-95% empirical coverage on load datasets.
-
CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
CausalVAE plug-in for world models preserves factual prediction and boosts counterfactual retrieval, with large gains on physics benchmarks and recovered physical interaction trends.
-
Neural Computers
Neural Computers are introduced as a new machine form where computation, memory, and I/O are unified in a learned runtime state, with initial video-model experiments showing acquisition of basic interface primitives from traces.
-
UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
UI-Oceanus shows that continual pre-training on forward dynamics predictions from synthetic GUI exploration improves agent success rates by 7% offline and 16.8% online, with gains scaling by data volume.
-
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.
-
World Model on Million-Length Video And Language With Blockwise RingAttention
Presents open-source 7B models for million-token video and language understanding via Blockwise RingAttention, setting new benchmarks in retrieval and long video tasks.
-
Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments
Empirical comparison finds that self-supervised representations vary in capturing agent state and generalizing to new levels or textures depending on environment visuals and dynamics.
-
Shaping Belief States with Generative Environment Models for RL
Multi-step predictive generative models form stable belief states capturing environment layout and agent pose, yielding higher data efficiency on RL tasks than model-free agents.
-
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
EfficientTDMPC extends the TD-MPC family with model ensembles, return averaging, and uncertainty penalties to reach SOTA sample efficiency on hard continuous control benchmarks in low-data regimes.
-
The Global Neural World Model: Spatially Grounded Discrete Topologies for Action-Conditioned Planning
GNWM maps environments to a discrete 2D grid with snapping to stabilize autoregressive planning and learns generalized dynamics from maximum-entropy random walks.
-
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
An event-centric framework encodes environments as semantic events and retrieves weighted prior maneuvers from a knowledge bank to enable interpretable, physics-aware decision-making for UAVs.
-
Convolutional Reservoir Computing for World Models
RCRC uses untrained random CNNs and reservoir computing plus evolution strategies to reach claimed state-of-the-art scores in reinforcement learning tasks while avoiding data storage and heavy training.
-
LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems
A survey taxonomy of LLMs identifies three scaling crises and six efficiency paradigms while tracing the shift from generation to tool-using agents.
- Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds
- Learning to Theorize the World from Observation
- Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training