← Back to all news
arXiv Machine Learning By Xunkai Li, Xu Wang, Yinlin Zhu, Xiong Yongfu, Yi Liu, Rong-Hua Li, Guoren Wang

ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models

Read the original on arXiv Machine Learning →

ICE (Interaction-aware Clifford Encoder) is a multimodal graph foundation model that uses a node-indexed Clifford latent field to encode topology, text, and images into explicit Cl(3) addresses. Edge-aware geometric products transform these directions into scalar, bivector, and trivector relations over observed neighborhoods, preserving entity semantics while enabling higher-order transport and direct field access. Across eleven graphs and multiple node‑classification, link‑prediction, and few‑shot tasks, ICE outperforms all 30 reported supervised and few‑shot comparisons, with core removals and mechanism controls demonstrating the importance of its higher‑order structure and semantic protection.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
1d ago

Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Models

The paper introduces FedCORE, a federated adaptation framework for multimodal graph foundation models that jointly optimizes perception (Encoder) and reasoning (GNN) modules via a shared low‑dimensional latent state. Unlike prior methods that freeze the Encoder, FedCORE allows both components to adapt together, addressing the dependency between multimodal evidence extraction and graph‑based relational reasoning. Experiments show that FedCORE significantly narrows the Encoder–GNN pairing gap, achieving an 80.7% reduction compared to independent joint adaptation.

By Zekai Chen, Xun Wu, Hailin Zhang, Xunkai Li, Yu Liu, Kairui Yang, Muyan Huang, Xuaner Chen, Rong-Hua Li, Guoren Wang
multimodal
More like this →
arXiv Machine Learning
Jul 20

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

arXiv:2607. 15687v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs.

By Xunkai Li, Guohao Fu, Yuming Ai, Zhengyu Wu, Hongchao Qin, Rong-Hua Li, Guoren Wang
fine-tuningmultimodalsafety
More like this →
arXiv Computer Vision
Sep 16

Hub-Spectral Activation of Latent Multimodal Knowledge

arXiv:2609.17094v1 Announce Type: new Abstract: Multimodal representation learning seeks shared representations for cross-modal retrieval and knowledge transfer. Hub-based binding reduces pairwise su...

By Ying Guo, Haidong Chen, Linrui Xu, Xiaohao Liu, Chuancheng Shi, Canran Xiao, Dan Zhang, Fei Shen, Li Shen, Tat-Seng Chua
multimodalsafety
More like this →
arXiv Machine Learning
Jul 22

One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models

arXiv:2607. 19128v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored.

By Jiayi Yang, Yifang Chen, Yuanfu Sun, Jiajin Liu, Qiaoyu Tan
llmsragmultimodalbenchmarks
More like this →