Youqi WU

2 accepted papers

2026

Revealing Differences in Multi-Modal Embeddings via Constrained Kernel Analysis

Youqi WU, Mohammad Jalali, Farzan Farnia

ICML 2026poster

Multi-modal representation models such as CLIP, SigLIP, and their variants are widely used to represent data across multiple modalities in modern learning systems. While these models are commonly evaluated through downstream performance, the analysis of their structural differences in how multi-moda…

Cited by 0 Source ↗Scholar ↗

2025

When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product

Youqi WU, Jingwei Zhang, Farzan Farnia

NeurIPS 2025poster

State-of-the-art embeddings often capture distinct yet complementary discriminative features: For instance, one image embedding model may excel at distinguishing fine-grained textures, while another focuses on object-level structure. Motivated by this observation, we propose a principled approach to…

Cited by 0 Source ↗code ↗Scholar ↗