Sparse Planning in Visual World Models via Cost Gradients
Read the original on arXiv Machine Learning →The paper introduces COSTGRAD, a training‑free, goal‑conditioned selector that ranks spatial tokens by the gradient norm of the planning cost, enabling sparse token usage in token‑based world models. On AdaLN‑conditioned predictors at 50% sparsity, COSTGRAD matches or surpasses full‑token planning on three of four continuous‑control benchmarks while delivering a 2.6× wall‑clock speedup per planning step. Combining token sparsity with reduced CEM search yields an overall ~5× speedup, though the method’s effectiveness depends on the underlying architecture, as shown by a failure mode with concat‑based models.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.