Showing 2026Show all
2 papers · 1 filter
cs.CV2026
MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
Juan Li, Chuanghao Ding, Xujie Zhang +1
Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can b…
cs.IR2026
LLMs Meet Isolation Kernel: Lightweight, Learning-free Binary Embeddings for Fast Retrieval
Zhibo Zhang, Yang Xu, Kai Ming Ting +1
Large language models (LLMs) have recently enabled remarkable progress in text representation. However, their embeddings are typically high-dimensional, leading to substantial stor…