Parallel Predictive World Models for Accurate and Efficient Long-Horizon Planning
We introduce Parallel Predictive World Models (PPWM), which predict a finite-horizon trajectory in parallel while retaining causal interaction among future representations.
ProofPaper ↗
Key points
- Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model.
- This preserves temporal structure but creates a horizon-length sequential path and exposes later predictions to recursive decoded-state feedback.
- We formalize this distinction by viewing autoregressive rollout as a causal trajectory map and identifying the decoded-state feedback pathway removed by PPWM.
- These results suggest that accurate and efficient long-horizon world-model planning does not require state-by-state autoregression, but can instead be achieved through parallel causal trajectory prediction.
Sources (1)
- [1]Parallel Predictive World Models for Accurate and Efficient Long-Horizon PlanningarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 04:26 PM
We introduce Parallel Predictive World Models (PPWM), which predict a finite-horizon trajectory in parallel while retaining causal interaction among future representations.
Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 6, 2026Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models
- Oct 6, 2026SPW-Nav Streams Language-Guided Panoramic Video in Real Time
- Oct 5, 2026From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
- Sep 29, 2026Introducing Quine: An AI research system designed for the complexity of biology
- Sep 29, 2026LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation
- Jun 9, 2026Powering the future of robotics in Europe