AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning

Sahil Mishra, Srinitish Srinivasan, Sourish Dasgupta, Tanmoy Chakraborty

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 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
use Polaris polar hyperspherical embedding instead of strongest baselinetaxonomy expansion · EnvironmentMean rank: 27.1 -> 6.48Improved
use Polaris instead of STEAMtaxonomy expansion · MeSH (multi-parent)H@1: 18.2 -> 33.56Improved
use Polaris instead of STEAMtaxonomy expansion · MeSH (multi-parent)mean rank: 372.6 -> 300.40Improved
use Polaris instead of STEAMtaxonomy expansion · SemEval-FoodR@1 and MRRHurt
use Polaris instead of STEAMtaxonomy expansion · SemEval-VerbH@1: 12.6 -> 14.43Improved
use Polaris instead of Gumbel Boximage-to-label ranking · CUB-200-2011 subsetPrecision@1: 73.93 -> 78.91Improved
use Polaris instead of STEAMtaxonomy expansion · ScienceR@1: 34.8 -> 46.18Improved

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