The authors evaluated whether latent sub-goals produced by a leading hierarchical JEPA planner were physically realisable, using a decoder-free measure they call the realisability residual.
Retrieving real states improves long-horizon planning over generated latent sub-goals
Metro-WM routes through observed frames from offline experience, avoiding physically unrealisable latent targets while enabling rapid replanning.
Big Tech
Royson Lee · Fady Rezk · Titouan Parcollet · Timothy Hospedales · Cristina Cornelio
Samsung AI · University of Edinburgh
Research Digest··2 min read
Lee et al.
Why this paper
From Samsung AI and University of Edinburgh
In one line
Retrieving sub-goals from recorded episodes outperforms generating latent sub-goals for long-horizon planning.
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.
§