Index of place names

Gazetteer

Every key term in the atlas, A to Z, with the territories where you will meet it. 111 terms across 21 territories.

A

action T-01 World Models: An Overview
action conditioning T-11 Video World Models I: Generation & Rollout
action effects T-20 World Models for Digital Agents
action tokens T-17 World Models for Robots II: Vision-Language-Action & World-Action Models
actor-critic T-10 Learning in Imagination: Policy & Value
adversarial training T-06 Generative Foundations: Latent Variables, Diffusion & Flow

B

belief T-02 History, Foundations & Probabilistic Formulation
belief state T-18 LLMs as World Models: Simulation, State Tracking & Grounding
branching search T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute

C

calibration T-21 Evaluating World Models: Utility, Robustness & Open Problems
causal rollout T-11 Video World Models I: Generation & Rollout
chain of thought T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute
closed-loop T-03 Environments, Simulators & Rollouts
closed-loop drift T-12 Video World Models II: Interaction, Memory & Efficiency
computer use T-20 World Models for Digital Agents
conservation laws T-15 Neural Physics & Learned Dynamics
context window T-12 Video World Models II: Interaction, Memory & Efficiency
contrastive learning T-05 Representation Learning
controllability T-21 Evaluating World Models: Utility, Robustness & Open Problems
coordinate frames T-13 Spatial World Models I: Geometry & 3D Representations

D

deformation fields T-14 Spatial World Models II: 4D Dynamics & Interaction
deliberation T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute
denoising T-07 Diffusion & Flow Matching
depth T-13 Spatial World Models I: Geometry & 3D Representations
diffusion T-06 Generative Foundations: Latent Variables, Diffusion & Flow
domain randomization T-16 World Models for Robots I: Simulation, Control & Sim-to-Real
drift T-21 Evaluating World Models: Utility, Robustness & Open Problems
dynamic occupancy T-14 Spatial World Models II: 4D Dynamics & Interaction

E

ELBO T-06 Generative Foundations: Latent Variables, Diffusion & Flow
embedding T-05 Representation Learning
emergent representations T-18 LLMs as World Models: Simulation, State Tracking & Grounding
encoder T-08 Latent World Models
environment interface T-03 Environments, Simulators & Rollouts
environment state T-20 World Models for Digital Agents

F

filtering T-04 State-Space Models
flow matching T-06 Generative Foundations: Latent Variables, Diffusion & Flow
flow-based action heads T-17 World Models for Robots II: Vision-Language-Action & World-Action Models
forward noising T-07 Diffusion & Flow Matching

G

Gaussian splats T-13 Spatial World Models I: Geometry & 3D Representations
generalist policies T-17 World Models for Robots II: Vision-Language-Action & World-Action Models
graph networks T-15 Neural Physics & Learned Dynamics
grounding T-18 LLMs as World Models: Simulation, State Tracking & Grounding
guidance T-07 Diffusion & Flow Matching

I

imagination-based training T-09 Model-Based Reinforcement Learning, Planning & Control
imagined rollout T-10 Learning in Imagination: Policy & Value
interactive 3D T-14 Spatial World Models II: 4D Dynamics & Interaction
interactive generation T-12 Video World Models II: Interaction, Memory & Efficiency
intervention T-21 Evaluating World Models: Utility, Robustness & Open Problems
irreversible actions T-20 World Models for Digital Agents

J

joint-embedding prediction T-05 Representation Learning

K

KL balancing T-08 Latent World Models

L

lambda-return T-10 Learning in Imagination: Policy & Value
latency T-21 Evaluating World Models: Utility, Robustness & Open Problems
latent actions T-12 Video World Models II: Interaction, Memory & Efficiency
latent state T-02 History, Foundations & Probabilistic Formulation T-08 Latent World Models T-11 Video World Models I: Generation & Rollout
latent variable T-06 Generative Foundations: Latent Variables, Diffusion & Flow
learned simulators T-15 Neural Physics & Learned Dynamics
long-range memory T-04 State-Space Models

M

masked prediction T-05 Representation Learning
model predictive control T-09 Model-Based Reinforcement Learning, Planning & Control T-16 World Models for Robots I: Simulation, Control & Sim-to-Real
MuZero T-10 Learning in Imagination: Policy & Value

N

neural operators T-15 Neural Physics & Learned Dynamics

O

object permanence T-14 Spatial World Models II: 4D Dynamics & Interaction
observation T-01 World Models: An Overview
occupancy T-13 Spatial World Models I: Geometry & 3D Representations
open-loop T-03 Environments, Simulators & Rollouts
out-of-distribution T-21 Evaluating World Models: Utility, Robustness & Open Problems

P

partial observability T-02 History, Foundations & Probabilistic Formulation
persistent memory T-12 Video World Models II: Interaction, Memory & Efficiency
physical priors T-15 Neural Physics & Learned Dynamics
pixel state T-11 Video World Models I: Generation & Rollout
planning T-01 World Models: An Overview T-09 Model-Based Reinforcement Learning, Planning & Control
point clouds T-13 Spatial World Models I: Geometry & 3D Representations
policy T-09 Model-Based Reinforcement Learning, Planning & Control T-10 Learning in Imagination: Policy & Value
prediction T-01 World Models: An Overview
prior and posterior T-08 Latent World Models
probing T-18 LLMs as World Models: Simulation, State Tracking & Grounding

R

radiance fields T-13 Spatial World Models I: Geometry & 3D Representations
real-time inference T-12 Video World Models II: Interaction, Memory & Efficiency
real-world fine-tuning T-16 World Models for Robots I: Simulation, Control & Sim-to-Real
recurrence T-04 State-Space Models T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute
recurrent state T-08 Latent World Models
rollout T-03 Environments, Simulators & Rollouts
rollout stability T-15 Neural Physics & Learned Dynamics

S

sampling steps T-07 Diffusion & Flow Matching
scene flow T-14 Spatial World Models II: 4D Dynamics & Interaction
score T-07 Diffusion & Flow Matching
selective state T-04 State-Space Models
self-verification T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute
sim-to-real gap T-16 World Models for Robots I: Simulation, Control & Sim-to-Real
simulated environments T-20 World Models for Digital Agents
simulator T-03 Environments, Simulators & Rollouts
smoothing T-04 State-Space Models
state T-01 World Models: An Overview
state tracking T-18 LLMs as World Models: Simulation, State Tracking & Grounding
stochastic state T-08 Latent World Models
system identification T-16 World Models for Robots I: Simulation, Control & Sim-to-Real

T

temporal consistency T-11 Video World Models I: Generation & Rollout
test-time compute T-19 Reasoning Models: Deliberation, Recurrence & Test-Time Compute
text simulation T-18 LLMs as World Models: Simulation, State Tracking & Grounding
token state T-11 Video World Models I: Generation & Rollout
tracking T-14 Spatial World Models II: 4D Dynamics & Interaction
trajectory distribution T-02 History, Foundations & Probabilistic Formulation
transition T-01 World Models: An Overview

U

utility T-21 Evaluating World Models: Utility, Robustness & Open Problems

V

value function T-10 Learning in Imagination: Policy & Value
velocity field T-07 Diffusion & Flow Matching
VLA T-17 World Models for Robots II: Vision-Language-Action & World-Action Models

W

web agents T-20 World Models for Digital Agents
web-scale pretraining T-17 World Models for Robots II: Vision-Language-Action & World-Action Models
world-action models T-17 World Models for Robots II: Vision-Language-Action & World-Action Models