RESEARCH PAPER

Privileged Foresight Distillation: Zero-Cost Future Correction for World Action Models

Pengcheng Fang; Hongli Chen; Xiaohao Cai

Classification

View four quadrants
Major category
WAMs
Quadrant
Not assigned
Architecture
Not assigned
Prediction paradigm
Not assigned
Source review status
Not assigned

Category review. Future-enabled and current-only masks share a WAM backbone; privileged residual distillation transfers future-conditioned action corrections into action-only inference. It modifies a complete world-action policy, not a generic distillation building block. Reading evidence

AT A GLANCE

Contribution

Privileged Foresight Distillation (PFD) compares two attention masks on the same world-action backbone, then learns the future-enabled change in action velocity through an output adapter. Deployment uses only the current frame and corrected action denoising. The reported LIBERO mean improves by 1.15 percentage points over reproduced Fast-WAM, with a measured 5.15% cached-context latency overhead; the title's zero-cost wording does not mean zero additional computation.

Abstract

An abstract has not been added yet.

Affiliations

The University of Southampton; The University of Queensland