AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Efficient Diffusion Planning with Temporal Diffusion

Jiaming Guo, Rui Zhang, Zerun Li, Yunkai Gao, Shaohui Peng, Siming Lan, Xing Hu, Zidong Du, Xishan Zhang, Ling Li

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Guidance for conditional diffusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
select top-m candidate plans instead of retaining all candidates (ablation)TDP · Hopper (average over 3 datasets)normalized score: 60.73 -> 93.7Improved
keep top-8 candidates instead of only the best plan (ablation)TDP · Hopper (average over 3 datasets)normalized score: 93.2 -> 93.7No clear effect
add automatic replanning instead of fixed replanning intervals (ablation)TDP · Hoppernormalized scoreImproved
use value-based criterion instead of state-based criterion for replanning (ablation)TDP · Hoppernormalized scoreImproved
add temporal diffusion (plan reuse) instead of Diffuser at long replanning intervals (ablation)Diffuser · Hoppernormalized scoreImproved
replan every step instead of at longer intervals (ablation)TDP · Hopper Medium-Replaynormalized scoreHurt
use temporal diffusion plan refinement instead of replanning each stepDiffuser · Gym-MuJoCo and Kitchendecision frequency: 1.4 -> 15.4 HzImproved
use temporal diffusion planner instead of Decision DiffuserDecision Diffuser · Gym-MuJoCo and Kitchendecision frequency: 0.62 -> 15.4 HzImproved
use TDP instead of DiffuserDiffuser · D4RL locomotion averagenormalized score: 77.5 -> 79.4Improved
use TDP instead of DiffuserDiffuser · D4RL Kitchen averagenormalized score: 53.1 -> 61.3Improved
use TDP instead of Decision DiffuserDecision Diffuser · D4RL locomotion averagenormalized score: 81.8 -> 79.4No clear effect
use inverse dynamics model (TDP_Inv) instead of TDPTDP · D4RL locomotion averagenormalized score: 79.4 -> 82.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy