AI Paper Atlas

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

GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models

Weifeng Zhang, Wenyuan Zhao, Amir Hossein Rahmati, Yucheng Wang, Zhiyuan Wang, Chao Tian, Xiaoning Qian

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty

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 amortized network (ablation)GPan-LoRA · OBQA->Chem (large shift)ECE (%): 22.60 -> 11.31Improved
add amortized network (ablation)GPan-LoRA · OBQA->Phy (large shift)ECE (%): 26.15 -> 13.29Improved
add amortized network (ablation)GPan-LoRA · OBQA->Chem (large shift)NLL: 1.37 -> 1.19Improved
add amortized network (ablation)GPan-LoRA · OBQA (in-distribution)accuracy (%): 87.27 -> 86.66No clear effect
add weight sharing (ablation)GPan-LoRA · OBQA->Phy (large shift)ECE (%): 22.52 -> 13.29Improved
add weight sharing (ablation)GPan-LoRA · OBQA (in-distribution)accuracy (%): 84.73 -> 86.66Improved
add weight sharing (ablation)GPan-LoRA · OBQA->Chem (large shift)NLL: 1.34 -> 1.19Improved
add amortized network (ablation)GPan-LoRA · OBQA->ARC-C (small shift)ECE (%): 6.35 -> 6.46No clear effect
Bayesianize only the last LoRA layer instead of all layersGPan-LoRA · OBQA->Chem (large shift)ECE (%): 11.31 -> 14.37Hurt
replace BLoB with GPan-LoRABLoB · OBQA->Chem (large shift)ECE (%): 24.45 -> 11.31Improved
replace LAP with GPan-LoRALAP · OBQA->Chem (large shift)ECE (%): 14.59 -> 11.31Improved
replace LAP with GPan-LoRALAP · OBQA->ARC-E (small shift)accuracy (%): 88.01 -> 82.74Hurt

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