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

ViPRA: Video Prediction for Robot Actions

arXiv 25.11 2025 44.4 method, application

TLDR

ViPRA turns video prediction models into robot policies by predicting future visuals and latent actions, finetuning with few demonstrations.

Reasoning

The paper presents a novel pretraining-finetuning framework that leverages actionless videos for robot control, showing strong empirical gains on both simulated and real-world tasks. However, it relies on teleoperated demonstrations for finetuning and does not explicitly claim to be a world model, limiting direct relevance to the specified keywords.

Read-first score

Read-first score 44.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 18.

Recency 8%
86.7

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

Methodology quality 25%
60

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

Reproducibility 25%
46

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Topical relevance 42%
25.7

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 371.

Keyword Scores

world dynamics prediction
6
video world model
5
world model
2
model-based reinforcement learning world model
2
world simulator
1
generative world model
1
interactive world model
1

Deep Analysis

Innovations

  • ViPRA: a pretraining-finetuning framework that learns continuous robot control from actionless videos by predicting future visual observations and motion-centric latent actions as intermediate representations
  • Training latent actions using perceptual losses and optical flow consistency to ensure physically grounded behavior
  • Chunked flow matching decoder that maps latent actions to robot-specific continuous action sequences using only 100-200 teleoperated demonstrations
  • Explicitly models both what changes and how, unlike prior latent action works that treat pretraining as autoregressive policy learning

Methodology

ViPRA first pretrains a video-language model to predict future visual observations and motion-centric latent actions, using perceptual losses and optical flow consistency. For downstream control, a chunked flow matching decoder is fine-tuned with 100-200 teleoperated demonstrations to map latent actions to robot-specific continuous action sequences.

Key Results

ViPRA outperforms strong baselines with a 16% gain on the SIMPLER benchmark and a 13% improvement across real world manipulation tasks.

Tags