Representation Alignment from a Few Paired Data via Distilled Optimal Transport

arXiv:2610.12781 · cs.AI · Submitted 2026-10-08 · Read on arXiv

cs.AI

Submitted: 2026-10-08

Updated: 2026-10-08

Comments: Preprint

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 1× in this paper · explained in 1 episode
• Optimal Transport — 1× in this paper · explained in 5 episodes

Sources

• Word Translation Without Parallel Data
• Improving zero-shot learning by mitigating the hubness problem
• Model alignment using inter-modal bridges
• The Platonic Representation Hypothesis
• Relative representations enable zero-shot latent space communication
• SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
• Offline bilingual word vectors, orthogonal transformations and the inverted softmax
• Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems