AI Paper Atlas

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

FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models

Rosen Ting-Ying Yu, Nicholas Sung, Faez Ahmed

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 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
condition residual model on LF variance and quantiles, not only mean (ablation)FIRE · 31 MF benchmarksNRMSE Elo: about 250 Elo drop when removedImproved
use TFM residual instead of scratch-trained GP (ablation)FIRE (TabPFNv2.5 base) · 31 MF benchmarksElo: 774 -> 1000Improved
use TFM residual instead of random forest (ablation)FIRE (TabPFNv2.5 base) · 31 MF benchmarksElo: 738 -> 1000Improved
use TFM residual instead of XGBoost (ablation)FIRE (TabPFNv2.5 base) · 31 MF benchmarksElo: 605 -> 1000Improved
use one TFM per fidelity (recursive) instead of bi-level two surrogates (ablation)FIRE · 31 MF benchmarksElo and runtime: over 10x runtime, no accuracy gainNo clear effect
use TFM instead of GP as base model (ablation)FIRE · 31 MF benchmarksNRMSEImproved
replace TFM with GP in the FIRE framework (FIRE(GP)) (ablation)FIRE · 31 MF benchmarksEloMixed
add post-hoc ensembling of the residual TFM (ablation)FIRE · 31 MF benchmarksNRMSE Elo: inference time increases by an order of magnitudeImproved
use Mitra instead of TabPFN as TFM backbone (ablation)FIRE · 31 MF benchmarksNRMSEHurt
use RealTabPFN instead of TabPFNv2.5 (ablation)FIRE · 31 MF benchmarksNRMSENo clear effect
use FIRE on nested inputs rather than disjoint (ablation)FIRE and GP baselines · synthetic benchmarksElo and rankNo clear effect
use single-pass TabPFNv2.5 with fidelity token instead of FT-PFN or LC-PFNTabPFNv2.5 · LCBenchNRMSEImproved

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