Hierarchical World Models with Implicit Dynamics

Gaoyue Zhou; Yvonne Wu; Zichen Jeff Cui; Nicolas Ballas; Mido Assran; Lerrel Pinto; Yann LeCun

cs.ROOct 30, 2026

Hierarchical World Models with Implicit Dynamics

Authors: Gaoyue Zhou, Yvonne Wu, Zichen Jeff Cui, Nicolas Ballas, Mido Assran, Lerrel Pinto, Yann LeCun

Organizations: Courant Institute, New York University · Meta-FAIR · AMI Labs

Abstract

Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks remain hindered by cumulative errors and search complexity. Existing hierarchical methods often use rigid macro-actions or latent skills, leading to brittle representations and limited fine-grained control. We introduce ID-WM (Implicit Dynamics World Models), a hierarchical world model that decouples state-space reachability from local control. Our framework utilizes a high-level model to sample feasible transitions across the state manifold and a low-level world model as an inverse dynamics solver to ground these transitions into precise actions. This allows the planner to identify reachable subgoals without being constrained by low-level execution details. By prioritizing local physical feasibility over global behavioral patterns, ID-WM synthesizes novel long-horizon plans from short segments, transcending the specific behavioral modes seen during training. We demonstrate its effectiveness across three navigation and manipulation suites, achieving a 38.5% improvement over state-of-the-art policy and diffusion-based planners. Crucially, by leveraging this hierarchical structure to mitigate compounding errors, our approach yields a 135% performance gain over single-level world model MPC, particularly in complex, unseen configurations for long-horizon tasks. Videos can be viewed at https://id-wm.github.io

Figures & tables

Figure 1: Overview of ID-WM . Our hierarchical planning framework decouples state-space reachability from local control, eliminating the reliance on task-specific value functions or pre-trained policies. Planning proceeds in two interleaved stages: (1) high-level planning, which discovers a sequence of temporally abstract subgoals spaced $\Delta$ steps apart, and (2) low-level control, which leverages a world model as an inverse dynamics solver to extract executable actions between each subgoal.

Figure 2: Architecture of ID-WM . Given an initial observation $o_{0}$ and a goal $o_{g}$ , we optimize for both the sequence of subgoals $s_{0},\dots,s_{T\Delta}$ and the executable actions $a_{t}$ in an interleaved fashion. Here, $f_{hi}$ denotes the diffusion-based high-level world model and $f_{lo}$ denotes the deterministic, transformer-based low-level world model, both of which predict in latent space.

Figure 3: We evaluate ID-WM on three environment suites (Wall, PushT, Maze); from left to right: Wall, PushT, and the four maze sizes (U-, Medium, Large, Giant).

Figure 4: Diverse neighboring states generated with the high-level WM of ID-WM .

Figure 5: High-level subgoals planned by ID-WM . The planned sequence successfully guides the agent to the target goal while ensuring that consecutive subgoals satisfy local reachability constraints.

	PushT		PushT-Aug
Method	Fix	Rand.	Fix	Rand.
HWM	0.38	0.20	0.42	0.16
ID-WM	1.00	0.77	1.00	1.00

Table 2: Success rate of ID-WM and HWM on PushT environments with fixed (Fix) and random (Rand.) goals.

Figure 6: Diverse plans generated by ID-WM . The top and bottom rows illustrate distinct strategies: counterclockwise and clockwise rotations of the T-block, both resulting in successful task completion.

Figure 7: Planning performance with increasing task complexity. In a), we test ID-WM ’s ability on Maze with increasing sizes. In b), we test ID-WM on increasingly longer horizon PushT tasks.

Figure 8: Subgoals generated by ID-WM on a visual PushT task. The first column denotes the starting state, and the last shaded column denotes the desired goal state. ID-WM generates reliable, sequential subgoals that drive steady progress toward the goal state without any degenerate states.

Method	$d=25$	$d=50$	$d=75$	Random Goal
DINO-WM	0.84	0.16	0.00	0.00
HWM	0.96	0.46	0.14	0.02
ID-WM	0.90	0.60	0.50	0.26

Table 3: Success rate on vision-based PushT. For

d\in\{25,50,75\}

the goal is

d

steps away; Random Goal samples both the initial and goal states randomly.

Figure 9: Examples of sampled initial and goal state pairs for the Wall, PushT, Giant Maze, Large Maze, and U-Maze environments

Figure 10: Success rate with respect to CEM samples and noise regularization.

$\Delta$ \ #Subgoals	3	4	5	6	8	12	25
1	0.06	0.04	0.06	0.08	0.04	0.10	0.06
2	0.14	0.14	0.28	0.50	0.64	0.48	0.24
3	0.50	0.56	0.64	0.82	0.76	0.74	0.42
4	0.60	0.76	0.86	0.86	1.00	0.90	0.44
5	0.74	0.84	0.96	0.98	0.94	0.76	0.38

Table 4: Success rate on PushT-Aug (Random Goal) when sweeping the subgoal horizon

\Delta

(rows) and the number of subgoals per high-level plan (columns). The default configuration (

\Delta=5

, 5 subgoals) is underlined.

Method	PushT-Aug (Rand.)	Medium Maze
HIQL	307.4	34.1
GCBC	1014.9	336.8
Diffuser	N/A	287.8
H-Diffuser	713.9	169.4
SL-WM	312.5	229.5
ID-WM	234.7	163.9

Table 5: Average steps to success over successful trajectories (lower is better). N/A indicates that no trajectory succeeded.

Table 15

Method	Samples	Elites	Replans	Horizon	SR
SL-WM (CEM budget matched)	300	30	15	25	0.21
SL-WM (inference time matched)	300	30	45	25	0.28
ID-WM	300	30	15	5 (each level)	0.77

Table 8: Success rate on PushT (Random Goal) when matching either the CEM budget or the wall-clock inference time of SL-WM to ID-WM .

Table 17

Table 18

Table 19

Name	Value
lr	$3\mathrm{e}{-4}$
Discount factor $\gamma$	0.99
Expectile $\tau$	0.7
High-level $\alpha$	3.0
Low-level $\alpha$	3.0
Subgoal steps $k_{\mathrm{sub}}$	25

Table 15: Shared hyperparameters for HIQL across all evaluation environments.

Table 21

Model	Execution	PushT				PushT-Aug
		Fix Goal		Random Goal		Fix Goal		Random Goal
		SR	Cov	SR	Cov	SR	Cov	SR	Cov
Diffuser	execute plan + replan	0.00	0.03	0.00	0.03	0.28	0.37	0.06	0.19
Diffuser	execute one action + replan	0.00	0.11	0.00	0.06	0.04	0.27	0.02	0.15
Diffuser	execute plan	0.00	0.05	0.00	0.03	0.00	0.09	0.00	0.13

Table 18: Diffuser results across execution settings and PushT variants.

Model	Execution	PushT				PushT-Aug
		Fix Goal		Random Goal		Fix Goal		Random Goal
		SR	Cov	SR	Cov	SR	Cov	SR	Cov
H-Diffuser	execute plan + replan	0.38	0.28	0.00	0.08	0.56	0.51	0.46	0.36
H-Diffuser	execute one action + replan	0.00	0.25	0.02	0.11	0.56	0.56	0.26	0.50
H-Diffuser	execute plan	0.04	0.09	0.00	0.06	0.02	0.17	0.00	0.10

Table 19: H-Diffuser results across execution settings and PushT variants.

Figure 11: Training-time convergence of predicted future-state distributions for the PushT environment

Figure 12: Visualization of the induced state mappings by ID-WM and naive WM.

World Models for Robotics

World models for robotics predict how scenes and robot states change under actions to support planning, control, and learning.

See all 389 papers

Hierarchical Planning with Latent World Models
Apr 3, 2026Wancong Zhang, Basile Terver, Artem Zholus +7Hierarchical Planning Hierarchical Robot Control
FAIR at Meta · New York University · Mila - Québec AI Institute +1
MemWM: Associative Memory-Enhanced Latent World Models for Long-Horizon Planning
Oct 14, 2026Yuwei Sun, Siyu ZhuWorld Model Learning World Models for Robotics
Shanghai Academy of AI for Science · Fudan University
Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
Jun 19, 2026Tianqi Du, Qi Zhang, Yifei Wang +1Latent Dynamics Modeling World Models
State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Amazon AGI SF Lab · Institute for Artificial Intelligence, Peking University

Apr 3, 2026J/K move · Enter open · S save

Hierarchical Planning with Latent World Models

Wancong Zhang, Basile Terver, Artem Zholus, Soham Chitnis+6

FAIR at Meta · New York University · Mila - Québec AI Institute+1

Hierarchical Planning Hierarchical Robot Control Hierarchical World Models Long-Horizon Robotic Manipulation Model Predictive Control Latent World Models

Open paper AskPDF arXiv

World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, multi-stage tasks: prediction errors compound and naive search is exponential in the planning horizon. Hierarchy mitigates both by decomposing tasks into shorter, tractable subproblems; yet prior hierarchical approaches either amortize control into task-specific policies (hierarchical RL) or assume low-dimensional states and known dynamics (classical hierarchical MPC). We present Hierarchical Planning with Latent World Models (HWM), an architecture and planning paradigm for hierarchical model predictive control directly on visual world models trained solely via next-latent prediction. HWM learns world models at multiple temporal scales within a shared latent space, so predictions from the long horizon model serve as subgoals for the short horizon model via latent matching, without task-specific rewards or hierarchical policies. To keep long-horizon search tractable, HWM learns an action encoder that compresses primitive action chunks into latent macro-actions. On real-world Franka manipulation, HWM solves pick-and-place from a single goal image at 70% success vs. 0% for single-level planning. Across simulated push manipulation and maze navigation, HWM consistently improves performance on long-horizon tasks while requiring up to 3x less planning compute.

Abstract

World Models for Robotics

Explore similar work

Hierarchical Planning with Latent World Models

MemWM: Associative Memory-Enhanced Latent World Models for Long-Horizon Planning

Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning