The authors study planning with frozen latent world models (LeWM), where a pretrained predictor scores each candidate action by the distance from its predicted embedding to an encoded goal image.
Aiming at observed intermediate targets beats final-goal scoring in frozen world model planning
Anchored Planning retrieves a recorded segment and points the frozen planner at an observation shortly after its start, improving long-range control without any training.
Top University
Xvyuan Liu · Jianjie Fang · Chen Gao · Yong Li
Tsinghua University · Manifold AI
Research Digest··3 min read
The authors show that scoring predicted outcomes by their distance to the final goal can break latent world model planning even when dynamics are exact and short-horizon search is globally optimal, whenever the route to the goal initially moves away.
Why this paper
From Tsinghua University and Manifold AI
In one line
Aiming at an intermediate observed target instead of the final goal lets a frozen world model reach long-range goals that final-goal scoring misses.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
Concepts
§