AI Paper Atlas

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

Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning

Zhanghu Zhao, Daolang Huang, Xinyi Wen, Samuel Kaski

NeurIPS 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian view of meta-learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes IMBUE, an amortized Bayesian experimental design framework that conditions on in-context knowledge at deployment time so the design policy is not tied to its training prior or task distribution.

Problem

Existing amortized Bayesian experimental design methods are tied to the prior and task distribution used at training and cannot exploit additional information available at deployment.

Approach

Accepts two forms of additional deployment-time information (as stated in the abstract, which is truncated) through a unified knowledge encoding, enabling in-context conditioning of an amortized BED policy rather than retraining per prior.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
concatenate previous instances to ALINE at deployment only (no training exposure) (ablation)ALINE · CES K=5sPCE: 13.37 -> 13.07 (relevant); 13.37 -> 10.16 (irrelevant)Hurt
add mixed-regime relevant/irrelevant training (ALINE-aux) (ablation)ALINE* · CES K=5sPCE: irrelevant 10.16 -> 12.23; relevant 13.07 -> 13.52Improved
add instance-token interface (ablation)ALINE-aux · CES K=5sPCE: irrelevant 12.23 -> 12.97; relevant 13.52 -> 13.99Improved
add reliability filter (ablation)IMBUE w/o filter · CES K=5, irrelevantsPCE: 12.97 -> 13.14Improved
add reliability filter (ablation)IMBUE w/o filter · CES K=5, relevantsPCE: 13.99 -> 13.93No clear effect
add reliability filter on prior channel (ablation)IMBUE · Location FindingsPCENo clear effect
supply relevant previous instances (K=5) to IMBUEIMBUE · CESsPCE: 13.46 -> 13.93Improved
supply irrelevant previous instances (K=5) to IMBUEIMBUE · CESsPCE: 13.46 -> 13.14No clear effect
use retrieve-then-condition (top two instances) instead of all instances (ablation)ALINE-aux · CES K=5sPCE: irrelevant 12.23 -> 12.69; relevant 13.52 -> 13.29Mixed
add concatenated previous instances to DAD and RL-BOED (ablation)DAD, RL-BOED · CESsPCE: RL-BOED 14.34 -> 2.56 (K=5 relevant)Hurt

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