AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts

Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi

ICLR 2026 · Architectures and efficiency › Mixture of experts · approach: Expert routing and specialization

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
use adaptive Top-k(x) instead of fixed Top-k (min RMSE metric) (ablation)Top-k L2D, two-stage · California HousingRMSE and budget: RMSE 6.23 at budget 0.156 (4.77 entities) vs 6.21 at budget 0.2 (6 entities)Improved
use adaptive Top-k(x) instead of fixed Top-k (uniform average RMSE) (ablation)Top-k L2D, two-stage · California HousingRMSE_avg: 10.08 -> 8.53Improved
consult more or costlier entities under average-based metrics (ablation)Top-k L2D · California Housing, RMSE_avg and RMSE_w-avgRMSEHurt
defer to top-k experts (k>1) instead of a single expertTop-1 L2D baseline · California HousingRMSEImproved

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