AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference

Niels Leif Bracher, Lars Kühmichel, Desi R. Ivanova, Xavier Intes, Paul-Christian Bürkner, Stefan T. Radev

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Simulation-based inference · 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
detach summary state before the policy to avoid nested BPTT (ablation)JADAI · Location Finding (T=30, Q30)sPCE: 7.935 -> 12.708Improved
sample rollout length r instead of fixing r=30 (ablation)JADAI · Location Finding (T=30, Q30)sPCE: 13.186 -> 12.708Hurt
sample rollout length r instead of fixing r=30 (ablation)JADAI · Location Finding (intermediate horizon Q10)sPCE: 6.433 -> 6.783Improved
use full BPTT instead of truncated window W=5 (ablation)JADAI · Location Finding (Q30)sPCE: 12.536 -> 12.708Improved
use full BPTT instead of truncated window W=5 (ablation)JADAI · Location Finding (Q10)sPCE: 6.533 -> 6.783Improved
add design-prior pretraining before joint training (ablation)JADAI · Location Finding (T=30)sPCE: 12.348 -> 12.708No clear effect
anneal random-design mix-in instead of pretraining (ablation)JADAI · Location Finding (T=30)sPCE: 12.352 -> 12.708No clear effect
train with terminal horizon T=30 instead of T=20JADAI · Location Finding (evaluated at T=20)sPCE: 10.48 -> 10.90Improved
train with terminal horizon T=30 instead of T=10JADAI · CES (evaluated at T=10)sPCE: 14.76 -> 14.85Improved
train with terminal horizon T=30 instead of T=10JADAI · Location Finding (evaluated at T=10, K=2)sPCE: 6.47 -> 6.74Improved
use diffusion model instead of flow matching posteriorJADAI · MNIST Image Discovery (sigma=0)SSIM/NRMSE: 0.968 -> 0.988 SSIM (FM higher); NRMSE 0.177 vs 0.185Mixed
use learned policy instead of random designJADAI posterior network · MNIST Image Discovery (sigma=0)SSIM: 0.478 -> 0.968Improved

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