4 papers
Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning
Jinjin Guo, Yexin Li, Zhichao Huang +5
Large-scale multimodal contrastive learning has recently achieved impressive success in learning rich and transferable representations, yet it remains fundamentally limited by the…
FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning
Jiaoyang Li, Jun Fang, Tianhao Gao +5
Representation learning is fundamental to modern machine learning, powering applications such as text retrieval and multimodal understanding. However, learning robust and generaliz…
ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts
Zheyue Tan, Zhiyuan Li, Tao Yuan +13
Mixture-of-Experts (MoE) architectures have emerged as a promising approach to scale Large Language Models (LLMs). MoE boosts the efficiency by activating a subset of experts per t…
A Modality-Tailored Graph Modeling Framework for Urban Region Representation via Contrastive Learning
Yaya Zhao, Kaiqi Zhao, Zixuan Tang +3
Graph-based models have emerged as a powerful paradigm for modeling multimodal urban data and learning region representations for various downstream tasks. However, existing approa…