NeurIPS 2026 Papers

Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score on clean benchmarks. This leaves a major gap in comprehending their potential as world models. We present the first systematic study addressing this gap, analyzing four matched-capacity frontier video foundation models, V-JEPA 2.1, V-JEPA 2, VideoPrism, and VideoMAEv2, across five robustness axes relevant to their deployment as video world models: feature discriminability, corruption robustness, fine-grained discrimination, occlusion robustness, and sensitivity to temporal direction. Our evaluations establish that across all five axes, latent-prediction models form a distinct and consistent profile. They degrade more gracefully under pixel corruption, preserve usable class structure rather than mere geometric stability under occlusion, capture fine-grained physical contact cues without reconstructing pixels, and uniquely encode the arrow of time. These advantages can even survive task adaptation: a frozen V-JEPA 2 backbone with a lightweight attentive probe outperforms a fully fine-tuned VideoMAE and a supervised TimeSformer on corruption and occlusion robustness. Our extensive results offer concrete new evidence in favor of latent prediction for robust world modeling.

Goal-conditioned visual navigation has been a long-standing testbed for embodied AI. We study a natural language-conditioned variant, language-conditioned visual navigation (LCVN), in which an embodied agent must follow a natural language instruction given only an initial egocentric observation. Without access to goal images, the agent must rely on language to shape its perception and continuous control. We introduce the LCVN Dataset, a benchmark of 39,016 trajectories and 117,048 human-verified instructions spanning diverse environments and instruction styles. Building on this benchmark, we study two complementary paradigms: (i) latent-imagination policy learning, in which a diffusion-based world model (LCVN-WM) imagines future observations and an actor-critic agent (LCVN-AC) learns its policy entirely within the imagined latent space; and (ii) unified autoregressive prediction, in which a single multimodal backbone (LCVN-Uni) jointly predicts actions and observations in one forward pass over a shared token sequence. Experiments show that two paradigms offer complementary strengths: latent imagination produces more temporally coherent rollouts, whereas unified prediction generalizes better to unseen environments. Targeted ablations further isolate the contributions of language guidance, conditioning signals, and instruction style, clarifying when language grounding versus dynamics modeling is the performance bottleneck. Together, these findings position LCVN as a concrete testbed for studying how language, imagination, and decision-making interact in embodied agents.

World models have enabled interactive exploration of game environments and robotic manipulation, but physical engineering remains beyond their reach: real materials exhibit nonlinear constitutive laws, carry history-dependent internal state, undergo inertial dynamics, and may possess hierarchical structures spanning multiple length scales. We present LEIA (Learned Environment for Interactive Architected materials), a world model that lets engineers apply boundary conditions step by step and observe the resulting deformation and stress fields in real time. LEIA handles large three-dimensional unstructured meshes and generates autoregressive responses to user-specified loading. We introduce MicroPlate, a benchmark of architected plates spanning two regimes of microstructure modeling: architected lattices that resolve microstructure explicitly through three-dimensional geometry, and a homogeneous plate where microstructural change is modeled implicitly through internal degrees of freedom. MicroPlate is used to assess LEIA alongside four baseline methods across both regimes. Finally, we demonstrate that LEIA enables efficient candidate generation and ranking for fast surrogate-guided search for de novo designs of architected materials, with stress-accurate candidate ranking validated by finite element ground truth.

World models enable prediction, planning, and decision-making by learning internal simulators of environment dynamics. Although substantial progress has been made in world models from pixel-based observations, many physical systems are instead observed through vector-based measurements that are noisy and only partially informative of the underlying state. We introduce K-PWM, a Koopman-structured probabilistic world model for prediction and control under partial observation. K-PWM combines a parameterized Koopman-structured state-space model with a nonlinear observation decoder, and performs probabilistic latent-state inference directly through the learned model parameters rather than through a separately trained inference network. We train K-PWM using a generalized expectation conditional maximization (GECM) procedure with principled initialization. Across Gymnasium MuJoCo tasks, K-PWM improves sample efficiency, yields reliable long-horizon predictions, and supports downstream control through model predictive path integral (MPPI) control. These results suggest that structured probabilistic latent dynamics provide a useful route toward data-efficient world modeling and control in partially observable vector-valued settings.

Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a sequence of skills, formalized as hierarchical neural options. However, existing model-free hierarchical reinforcement algorithms need a lot of data. We propose a novel method, which we call "AgentOWL" (Option and World model Learning), that jointly learns --- in a sample efficient way --- an abstract world model (abstracting across both states and time) and a set of neural options. We show, on a subset of Object-Centric Atari games, that our method can learn more skills using less data than baseline methods and possesses learning and generalization capabilities that the baselines do not have.

We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred over another while the environment’s true transition model implies the reverse. We analogize our definition with a prior characterization of reward hacking but show that the associated proof of inevitability does not transfer to exploitation. To overcome this obstruction, we develop a general theory of reward hacking and model exploitation that proves that exploitation is essentially unavoidable on large policy sets and yields the corresponding claim for hacking as a special case. Unfortunately, we also find that the conditions that guarantee unhackability in finite policy sets have no counterparts that preclude exploitation. Consequently, we introduce a relaxed notion of exploitation and derive a safe horizon within which it can be avoided. Taken together, our results establish a formal bridge between reward hacking and model exploitation and elucidate the limits of safe planning in world models.

Modern AI agents can plan, reflect, reason, and act over long-horizon digital tasks. Even so, they cannot plan to steer a social interaction in real time. Doing so requires anticipating how latent factors like trust and resistance will evolve under the agent's actions, fast enough to plan within a conversational turn. Generative world models approach this by narrating possible futures, but autoregressive text generation is both too slow for real-time planning and fundamentally lossy. Representation-predictive methods can be superior, but are underexplored for interaction. We build LID-Bench, the first controlled testbed with oracle latent states for interaction dynamics, enabling systematic comparison of generative and representation-predictive world models against known dynamics. A bottleneck decomposition on three generative models spanning 117M--350M parameters reveals that all learn interaction dynamics internally, with text-rendering signal losses of 89--100\% observed by horizon $k{=}5$. Our representation-predictive model (Social-JEPA, 125M params, 500K trainable) bypasses text entirely, forecasting latent dynamics $2.8$--$3.9\times$ more accurately while performing rollouts $1{,}059$--$2{,}314\times$ faster---making real-time planning within conversational turn-taking latencies feasible.

Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment.

Neural surrogates promise large speedups over classical solvers for physical dynamics but fail silently at sharp dynamical events such as shocks, fronts, and contact. We present hybrid neural world models for physical dynamics: a recipe for training and deploying multi-horizon surrogates in physical state space, where a single network with continuous horizon conditioning is trained with direct supervision against textbook reference solvers to predict any future state at horizon $T$ in one forward pass. Although no part of the training data, loss function, or architecture supervises discontinuity location, the trained surrogate encodes it implicitly, recoverable from its forward passes alone as a per-trajectory error map that concentrates on shocks, fronts, and contacts, and stays small elsewhere. The map is competitive with or better than standard label-free baselines including deep ensembles, learned error heads, gradient-magnitude indicators, and locally-adaptive conformal prediction, while using only a single trained network and requiring no calibration set or governing-equation knowledge. The recipe supports two operating points. Mode 1 runs the surrogate alone for maximum throughput, with same-hardware CPU speedups of $26\times$ to $72\times$ against textbook solvers on the PDE environments. Mode 2 uses the error map to gate a reference-solver fallback, deferring uncertain trajectories and roughly halving the surrogate's residual error at the default operating point. The recipe applies without modification across reaction-diffusion, compressible Euler, and rigid-body collision dynamics.

Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across tasks such as summarization, question answering, retrieval-augmented generation, and agentic interaction. This fragmentation makes it unclear whether a mitigation that works in one setting actually reduces hallucinations across contexts. Current hallucination benchmarks either require human annotation and fixed references that may eventually be memorized, or rely on naturalistic observations which are often recorded in settings that are difficult to reproduce or test systematically. To enable further research on the root causes of hallucination, we introduce HalluWorld, an extensible benchmark framework grounded in an explicit reference-world formulation: a model hallucinates when it produces an observable claim that is false with respect to this reference world. Building on this view, we construct a family of synthetic and semi-synthetic benchmark environments in which the reference world is fully specified, the model's observable view is controlled, and hallucination labels can be generated automatically by construction. HalluWorld spans multiple settings that are classically representative for AI, i.e., gridworlds, chess, and realistic terminal tasks. This enables controlled variation of key factors such as world complexity, observability, temporal change, and source-conflict policy, allowing us to disentangle hallucinations into more fine-grained error categories. We evaluate frontier and open-weight language models across these settings and find consistent patterns across domains: perceptual hallucination on directly observed information is near-solved for frontier models, while multi-step state tracking and causal forward simulation are still difficult for frontier models, and are not generally solved by extended thinking. In the terminal setting specifically, models also struggle with when to abstain from answering. The uneven profile of failures across probe types and domains suggest that different hallucinations arise from qualitatively distinct failure modes rather than reflecting a single underlying capability. Our results suggest that controlled reference worlds offer a scalable and reproducible path toward measuring and reducing hallucinations in modern language models.

World models enable model-based planning through learned latent dynamics, but imagined rollouts often become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability arises from two missing structures in planner-facing latents: history-conditioned memory for approximate Markov completeness, and geometric organization that separates configuration, momentum, and task semantics. We propose HaM-World, a structured world model that decomposes the latent state into a canonical $(q, p)$ subspace and a context subspace $c$, while incorporating Mamba selective state-space memory as a history-conditioned input to the same latent dynamics. Within this unified interface, $(q, p)$ evolves under a Soft-Hamiltonian dynamics composed of an energy-derived Hamiltonian vector field and learnable residual and control dynamics, while $c$ captures semantic, dissipative, and non-conservative factors. This design provides the planner with a single latent representation shared across dynamics prediction, reward and value estimation, imagined rollouts, and cross-entropy method (CEM) planning. On four DeepMind Control Suite tasks, HaM-World achieves the highest average AUC (+9.5% over strong baselines), reduces long-horizon rollout error to 45% of a competitive model, and wins 11 out of 12 $k \in \{3,5,7\}$ rollout MSE metrics. Under 12 out-of-distribution perturbations, HaM-World consistently attains the highest returns, with average gains of 10.2% on Finger Spin and 13.6% on Reacher Easy. Mechanism diagnostics further demonstrate bounded energy drift under action-free rollouts, structured energy variation under policy control, and coherent control-induced energy transfer, supporting the effectiveness of the proposed Soft-Hamiltonian latent dynamics. Code: https://anonymous.4open.science/r/HaM_World-47CD

Multi-view bimanual robot world models must predict future observations while preserving scene identity, following two synchronized but non-exchangeable arms, and maintaining consistency between global and wrist-local views. Existing conditioning schemes often collapse left- and right-arm actions into a view-agnostic control signal, making long-horizon rollout prone to scene drift, wrong-arm responses, and cross-view inconsistency. We propose \textbf{HAI}, a \textbf{Hierarchical Anchored Interaction} architecture for controllable multi-view bimanual world modeling. HAI organizes prediction as a structured information flow. First, hierarchical action-view conditioning routes the bimanual action chunk to camera streams, injects coarse chunk-level intent, performs structured multi-view modeling on the coarse-modulated features, and then injects fine per-frame action control. Second, anchored dynamic generation fuses the fine action-conditioned descriptors with persistent per-view scene anchors before decoding future observations. Experiments on AgiBot and DROID show that HAI improves long-horizon rollout quality over the baselines. Ablations confirm gains in scene stability, wrist-view controllability, and cross-view consistency. Further experiments on policy-improvement diagnostics indicate more useful synthetic rollout signals for downstream VLA policies, achieving an averaging 67.2\% relative gain in success rate. The project page is available at \url{https://hai-anon.github.io/}.

Autoregressive world models have emerged as a powerful paradigm for interactive video generation, allowing users to navigate dynamically generated environments through actions. These models are typically conditioned on a text prompt and/or a single reference frame, from which the entire world is generated. Yet the moment the user navigates beyond what is visible in that frame, the unseen regions are populated by the base model's priors, with no mechanism for the user to specify what should appear and where. This is a fundamental limitation for applications such as gaming, interactive storytelling, and simulation, where controllable scene composition is essential. We refer to this missing capability as concept spawning; introducing a user-specified visual concept into a world model, analogous to spawning in a game engine. We introduce SPAWN (Swapping Pinned Anchor with Windowed iNjection), a training-free method for concept spawning. SPAWN exploits a structural property of image-to-video backbones: the first slot of the context memory is pinned to the reference frame and acts as a foundational anchor for every generated chunk. By swapping this anchor with an external concept latent over a short injection window and letting the original anchor return, we cause the concept to propagate naturally through the rollout via the model's own memory. SPAWN supports concepts from fine-grained entities such as characters and props to large-scale elements such as buildings and landmarks, and accepts either a concept image or a text description as input. Experiments show that SPAWN integrates concepts with consistent lighting, scale, and perspective while preserving identity and temporal coherence, demonstrating that controllable concept spawning is achievable in existing autoregressive world models without any training.

Continual Reinforcement Learning (CRL) requires agents to adapt to sequentially arriving tasks while retaining performance on previous ones. Most existing CRL methods rely on model-free frameworks, addressing catastrophic forgetting via regularization, parameter isolation, or experience replay. World models offer a promising alternative by accumulating transferable dynamics knowledge and enabling planning-based decision-making. However, existing world model approaches suffer from slow adaptation at task boundaries: abrupt reward shifts mislead the planner, fixed planning horizons accumulate prediction errors when the dynamics model is unreliable, and quality-agnostic replay dilutes training while exacerbating forgetting. We propose HERD (Horizon-adaptive Elite Replay with reward Disagreement), which addresses these challenges from two complementary perspectives: for $\textbf{\emph{how to learn}}$, Uncertainty-aware Reward Planning leverages ensemble disagreement to accelerate reward calibration and guide exploration, while Adaptive Planning Horizon adjusts rollout depth based on dynamics prediction error to prevent error accumulation; for $\textbf{\emph{what to learn}}$, Elite Experience Replay applies quality-stratified reweighting of historical trajectories to strengthen knowledge retention. Together, these components $\textbf{\emph{accelerate new-task adaptation and mitigate catastrophic forgetting.}}$ Experiments on Continual World, Continual Bench, and DM Control show that HERD consistently outperforms existing methods in overall performance, forgetting mitigation, and new-task adaptation.

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting their effectiveness at deployment. We observe that execution itself provides a natural but underutilized signal: after each action, the robot directly observes the true next state, revealing the mismatch between predicted and actual outcomes. Building on this insight, we propose $\textbf{feedback world model}$, a new paradigm that closes the loop between prediction and observation at inference time. Instead of treating the world model as a static open-loop predictor, our method maintains a lightweight feedback state that is updated online to iteratively correct future predictions, compensating for model errors using real-time observations without additional training data or parameter updates. We show that this process can be interpreted as a latent-space observer and admits convergence guarantees under mild conditions. We further introduce action-aware guidance to better translate corrected predictions into control by emphasizing action-controllable components while suppressing irrelevant variations. Experiments on LIBERO-Plus, Robomimic, and real-world manipulation tasks demonstrate that our method substantially improves both prediction accuracy and policy performance under distribution shift. In particular, it reduces world model prediction error by up to 76.4\% and improves out-of-distribution (OOD) success rate by 30\%. These results show that incorporating real-time feedback at inference time provides a simple yet powerful alternative to static world modeling.

Latent world models based on Joint-Embedding Predictive Architecture (JEPA) are deterministic by design. While successful in fully observable scenarios, this paradigm breaks down when past observations and actions lead to multiple plausible future possibilities, e.g., due to occlusion. We introduce EpicWorldModel, a framework to train stochastic JEPAs for environments and tasks with inherent uncertainty under partially observability. We jointly train the EpicWorldModel predictor with its latent representation space to directly predict multiple potential future states using a flow-matching objective, when the goal-relevant scene content is absent from the conditioning history. We show that flow predictive variance approximates an upper bound on Expected Information Gain and serves as a useful exploration guidance for planning. By incorporating this uncertainty signal into Cross-Entropy Method (CEM)-based planning, our approach balances goal-reaching with exploration of uncertain regions where occluded or unseen goals are most likely to be located. We demonstrate the effectiveness of EpicWorldModel through a series of latent planning experiments with the best performance among all baseline methods, showing up to $22\%$ empirical improvement in success rate over LeWorldModel.

Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under changing meteorological conditions. In this paper, we view this task as a partially observed, weather-driven world modeling problem, in which weather acts as a conditioning signal, while forecasting remains uncertain due to sparse observations and unobserved land-surface states. However, existing methods do not fully capture this setting: deterministic models collapse uncertainty into a single future prediction, while diffusion-based methods typically treat weather variables as undifferentiated conditioning signals, and existing benchmarks focus mainly on reconstruction accuracy rather than whether forecasts respond correctly to changed weather forcing. We introduce EO-WM, a video diffusion transformer for multispectral EO forecasting. EO-WM incorporates a physically informed conditioning framework that represents meteorological forcing through a climatological baseline, weather anomalies, and cumulative physical stress signals. Specifically, it separates baseline and anomaly through distinct conditioning pathways, and accumulates anomalous forcing over time to capture sustained heat and drought stress. To evaluate weather-response behavior beyond standard metrics, we introduce two diagnostic benchmarks: an Extreme Summer Benchmark for severity-aware prediction of vegetation degradation under extreme weather, and a Seasonal Matched-Pair Benchmark for testing response fidelity under changed weather forcing. Experiments show that EO-WM reduces the error in predicted Normalized Difference Vegetation Index (NDVI) decline amplitude by a relative 5.63\% and improves directional hit rate by a relative 7.80\%, while remaining competitive on standard pixel-level metrics.

CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream---stdout, errors, file contents---records the consequences of its actions. We argue that this stream is a supervision signal, but standard agent RL largely discards it: GRPO-style training updates action tokens while ignoring environment responses, even though rollouts already contain them. We introduce ECHO (Environment Cross-entropy Hybrid Objective), an auxiliary loss that trains the policy to predict observation tokens alongside the policy gradient. ECHO reuses the same forward pass, requires no additional rollouts, and turns terminal feedback into a dense signal that remains informative even on failed trajectories. This objective shapes the policy toward a world model of terminal dynamics, plausibly improving its priors over which actions are likely to succeed. On TerminalBench 2, ECHO nearly doubles pass@1: Qwen3-8B improves from 2.70% to 5.17%, and Qwen3-14B from 5.17% to 10.79%. From base Qwen3-8B, ECHO+GRPO matches expert-SFT-then-GRPO on held-out terminal tasks without the expert demonstrations required for SFT, and closes roughly half this gap on TerminalBench 2. Without verifier rewards, ECHO can lead to self-improvement through exploration alone, suggesting environment observations are not merely context for actions but supervision for the policy itself.

Existing latent world models for autonomous driving have opened a promising path toward future-aware driving intelligence. However, they typically treat future latent states as prediction targets or auxiliary signals, rather than directly conditioning trajectory planning. This can entangle current and future features in latent space. In this work, we propose DriveFuture, a future-aware latent world modeling framework for autonomous driving that explicitly learns planning-oriented foresight by conditioning the current latent state modeling process on future world states. Specifically, during training, the model first predicts future latent world states from the current latent state and ego action, and then refines the prediction against the ground-truth future latent state via cross-attention. The resulting future-aware latent serves as an explicit condition for a diffusion-based trajectory planner. During inference, DriveFuture conditions on the predicted future latent state instead of the ground-truth future state. DriveFuture achieves SOTA performance on the public NAVSIM benchmarks, reaching 55.5 EPDMS on NAVSIM-v2 navhard, 89.9 EPDMS on NAVSIM-v2 navtest, and 90.7 PDMS on NAVSIM-v1 navtest, respectively. These results suggest that the key to latent world modeling lies not merely in simulating future states, but more importantly in conditioning current decision-making on future states. Notably, as of April 2026, DriveFuture ranks 1st on the NAVSIM-v2 navhard leaderboard and achieves SOTA performance on NAVSIM-v1 navtest.