Conditional Representation Learning for Customized Tasks

NeurIPSSpotlight2025

Authors
Honglin Liu, Chao Sun, Peng Hu, Yunfan Li, Xi Peng
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

representation learning

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive