AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making

Fan Feng, Selena Ge, Minghao Fu, Zijian Li, Yujia Zheng, Zeyu Tang, Yingyao Hu, Biwei Huang, Kun Zhang

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 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
add latent identification module (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -103.5 -> -73.5Improved
keep training the latent module (not frozen) (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -110.4 -> -73.5Improved
add backward refinement step (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -82.0 -> -73.5Improved
add zig-zag sampling (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -91.6 -> -73.5Improved
use causal (increasing) noise schedule instead of same noise level (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -89.7 -> -73.5Improved
add backward refinement step (ablation)Ada-Diffuser policy · LIBEROsuccess rate: 83.9 -> 93.4Improved
add zig-zag sampling (ablation)Ada-Diffuser policy · LIBEROsuccess rate: 91.4 -> 93.4Improved
add latent module (ablation)Ada-Diffuser policy · LIBEROsuccess rate: 89.3 -> 93.4Improved
increase latent dimension to 4x-6x (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -73.5 -> -102.4 (6x)Hurt
vary latent dimension within 0.5x-2x (ablation)Ada-Diffuser planner · Cheetah-Wind-Snormalized return: -85.2 (0.5x), -77.6 (2x) vs -73.5No clear effect
add latent factor modeling to DF plannerDF · Cheetah-Wind-Enormalized return: -105.8 -> -68.9Improved
Ada-Diffuser vs plug-in DynaMITE context moduleDF · Ant-Dir-Enormalized return: 266.7 -> 285.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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