6 papers
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Ang Li, Ben Liu, Bin Han +215
Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…
FedSM: Robust Semantics-Guided Feature Mixup for Bias Reduction in Federated Learning with Long-Tail Data
Jingrui Zhang, Yimeng Xu, Shujie Li +5
Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID…
GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations
Junze Chen, Cheng Yang, Shujie Li +4
Large language models (LLMs) have demonstrated their strong capabilities in various domains, and have been recently integrated for graph analysis as graph language models (GLMs). W…
Blend the Separated: Mixture of Synergistic Experts for Data-Scarcity Drug-Target Interaction Prediction
Xinlong Zhai, Chunchen Wang, Ruijia Wang +7
Drug-target interaction prediction (DTI) is essential in various applications including drug discovery and clinical application. There are two perspectives of input data widely use…
HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs
Shujie Li, Yuxia Wu, Chuan Shi +1
Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many real-world graphs exhibit heterophily,…
Exploring the Potential of Large Language Models for Heterophilic Graphs
Yuxia Wu, Shujie Li, Yuan Fang +1
Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the va…