Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making

ICML 25 2025 53.4 method

TLDR

FOUNDER integrates foundation models with world models for open-ended embodied decision making, using a mapping function and temporal distance reward.

Reasoning

The paper presents a novel framework combining foundation models and world models, with strong empirical results on multi-task benchmarks. However, the abstract lacks details on limitations and scalability, and the reliance on offline data may limit real-world applicability.

Read-first score

Read-first score 53.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 44.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Topical relevance 42%
62.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 25%
50

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 461.

Keyword Scores

world model
9
world simulator
8
model-based reinforcement learning world model
8
world dynamics prediction
7
generative world model
5
video world model
4
interactive world model
3

Deep Analysis

Innovations

  • Integration of Foundation Models and World Models for open-ended embodied decision making in a reward-free manner
  • Learning a mapping function that grounds FM representations into the WM state space, enabling inference of physical states from external observations
  • Using predicted temporal distance to the goal state as an informative reward signal for goal-conditioned policy learning through imagination

Methodology

FOUNDER learns a mapping function that aligns Foundation Model representations with the state space of a World Model, allowing the agent to infer its physical state from observations. This mapping enables goal-conditioned policy learning via imagination, where the predicted temporal distance to the goal state serves as a reward signal, eliminating the need for external rewards.

Key Results

FOUNDER achieves superior performance on multi-task offline visual control benchmarks, particularly in tasks with complex observations or domain gaps where prior methods struggle. The learned reward function is empirically validated to be consistent with ground-truth rewards.

Tags