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

MODIP: Efficient Model-Based Optimization for Diffusion Policies

arXiv 2026 47 method, application

TLDR

MODIP uses a world model and MPC to efficiently fine-tune diffusion policies offline-to-online, outperforming baselines on D4RL and RoboMimic.

Reasoning

The paper presents a novel framework that addresses the challenge of RL fine-tuning for diffusion policies by leveraging a world model for trajectory generation and policy adaptation. Strengths include efficiency gains via terminal state value and policy-independent critics; weaknesses include limited evaluation to simulated tasks and potential scalability issues.

Read-first score

Read-first score 47, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 20.

Recency 6%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Citation impact 18%
95.6

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.95592828

Methodology quality 18%
60

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

Reproducibility 18%
30

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

Topical relevance 29%
28.6

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

Citation velocity 12%
0

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FoundationFrontierBridge

Rank sensitivity

Stability: volatile; rank range: 402.

Keyword Scores

world model
9
model-based reinforcement learning world model
5
world dynamics prediction
3
world simulator
1
generative world model
1
interactive world model
1
video world model
0

Deep Analysis

Innovations

  • MODIP framework for offline-to-online fine-tuning of diffusion policies using a world model to guide policy adaptation
  • Use of model predictive control (MPC) to generate high-quality trajectories within the world model as supervised targets for fine-tuning
  • Terminal state value instead of policy-dependent state-action value to reduce MPC inference time
  • Policy-independent TD targets for training critics to reduce training time

Methodology

MODIP leverages a world model to guide policy adaptation of diffusion policies. It uses model predictive control (MPC) to generate high-quality trajectories within the world model, which serve as supervised targets for fine-tuning the diffusion policy. To improve efficiency, MODIP employs a terminal state value instead of a policy-dependent state-action value for MPC planning and trains critics with policy-independent TD targets.

Key Results

Experiments on D4RL (MuJoCo, Kitchen) and RoboMimic tasks show that MODIP improves diffusion policies beyond behavioral cloning and is competitive with or outperforms diffusion policy RL fine-tuning methods and strong model-based baselines such as TD-MPC2.

Tags

diffusion policiesrobot learningmodel predictive controlworld modelreinforcement learningimitation learningLG