We have 11 of 38 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Multimodal graph foundation models (MGFMs) seek to learn generalizable representations from large-scale graphs with heterogeneous node modalities. However, real-world Multimodal-Attributed Graphs (MAGs) often contain incomplete node attributes, limiting the scale and diversity of available pretraining corpora. Besides,...
Multimodal graph learning has recently emerged as an effective paradigm for in corporating inter-entity relationships into multimodal representations. Existing studies have made substantial progress on how to construct and optimize graphs, but rarely consider a more fundamental question: whether additional relational s...
Recent text-to-motion models have improved motion quality and instruction following, yet many-step denoising and large model components make deployment slow and memory-intensive. We present Terminal-Amplification-Controlled Distillation (TACD), an on-policy approach for training efficient motion generators from text pr...
This empirical study shows that candidate rankings change with the selected input, while predicted probabilities remain informative after the class stops changing, and leads to GraphSelect, which starts from individual candidate gains and refines the subset through jointly evaluated exchanges.
Graph-Optimized Multimodal Alignment (GOMA), which lets a jointly trained model support single-modality and dual-attribute retrieval through a task-specific readout, achieves state-of-the-art performance on all 14 primary measures against 14 external methods.
This work introduces ICE (Interaction-aware Clifford Encoder), a multimodal graph foundation model built on a node-indexed Clifford latent field that ranks first in all 30 reported supervised and few-shot comparisons.
AdaFGC is proposed, an Adaptive Federated graph clustering framework based on Global community-aware Contrastive learning that introduces an over-complete set of global community anchors to model the global community structure and adaptively estimate clustering cardinality via cross-client anchor refinement.
BRAIN is a unified model that focuses on graph context that combines neighborhood scope with modality composition that improves node-classification and link-prediction performance and achieves an average relative improvement of 14.72% across four graph-to-text and two graph-to-image metrics.
FedOGL preserves historical decision behavior through replay and task-start distillation, while protecting graph-propagation memory via projection onto a globally shared structure basis via projection onto a globally shared structure basis.
Federated multimodal graph learning with Topology-aware Cross-modal Routing (FedTCR) is proposed, the first systematic algorithm designed for FMGL and outperforms state-of-the-art baselines on both graph-centric and modality-centric tasks.
A multimodal federated graph unlearning framework built around target-specific representation decoupling that effectively removes requested information, preserves retained graph utility, and achieves a speedup over full retraining.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
