AI Paper Atlas

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

Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models

Hulingxiao He, Zhi Tan, Yuxin Peng

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2 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
add TARA alignment to No-Thinking RFTQwen3-VL-2B · iNat21-PlantHCA: 9.23 -> 12.78Improved
add TARA alignment to No-Thinking RFTQwen2.5-VL-3B · iNat21-AnimalHCA: 21.99 -> 24.02Improved
add TARA alignment on novel speciesQwen3-VL-2B · TerraIncognita novelOrder F1: 23.30 -> 33.45Improved
add TARA alignment on novel species at family levelQwen3-VL-2B · TerraIncognita novelFamily F1: 11.47 -> 12.67No clear effect
add label alignment LC (first answer token) on top of visual alignment LV (ablation)TARA · iNat21-PlantHCA: 10.72 -> 12.78Improved
add LC alignment on top of LV (ablation)TARA · iNat21-Plantleaf accuracy: 33.27 -> 32.66No clear effect
move LC alignment to layer 28 from layer 14 (with LV at 14) (ablation)TARA · iNat21-PlantHCA: 10.40 -> 12.78Improved
use all visual tokens instead of last visual token for LV (ablation)TARA · iNat21-PlantHCA: 10.30 -> 12.78Improved
use first answer token instead of last question or mean answer tokens for LC (ablation)TARA · iNat21-PlantHCA: 12.01 -> 12.78 (last question token), 11.59 -> 12.78 (mean answer)Improved
add TARA alignment to No-Thinking RFTQwen3-VL-2B · ImageWikiQAaccuracy: 48.70 -> 51.40Improved

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