Inputs For each reuse-eligible timestep 𝑡∈ T cache, we are given Scal (𝑡)= n (𝑠 (𝑖) 𝑡 , 𝜖 (𝑖) 𝑡 ) o 𝑁 𝑖=1 , 𝑁=4096,(55) constructed as in Appendix E

Split-conformal regression details:This subsection specifies the complete split-conformal construction used to map probe-based scores to high-probability upper bounds on potential reuse error magnitudes · 2048

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

citation-role summary

method 1

citation-polarity summary

use method 1

representative citing papers

Muninn: Your Trajectory Diffusion Model But Faster

cs.RO · 2026-05-11 · unverdicted · novelty 7.0

Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.

citing papers explorer

Showing 1 of 1 citing paper.

Muninn: Your Trajectory Diffusion Model But Faster cs.RO · 2026-05-11 · unverdicted · none · ref 97
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.

Inputs For each reuse-eligible timestep 𝑡∈ T cache, we are given Scal (𝑡)= n (𝑠 (𝑖) 𝑡 , 𝜖 (𝑖) 𝑡 ) o 𝑁 𝑖=1 , 𝑁=4096,(55) constructed as in Appendix E

citation-role summary

citation-polarity summary

fields

years

verdicts

roles

polarities

representative citing papers

citing papers explorer