collaborators

7 papers

cs.CL2025

Structure and Destructure: Dual Forces in the Making of Knowledge Engines

Yihong Chen

The making of knowledge engines in natural language processing has been shaped by two seemingly distinct paradigms: one grounded in structure, the other driven by massively availab…

cs.IR2025

Distance-aware Self-adaptive Graph Convolution for Fine-grained Hierarchical Recommendation

Tao Huang, Yihong Chen, Wei Fan +2

Graph Convolutional Networks (GCNs) are widely used to improve recommendation accuracy and performance by effectively learning the representations of user and item nodes. However,…

cs.LG2025

Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency

Binwen Liu, Peiyu Xu, Quan Yuan +1

We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear…

cs.CL2025

Multilingual Language Model Pretraining using Machine-translated Data

Jiayi Wang, Yao Lu, Maurice Weber +5

High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as LLMs still under…

cs.LG2024

AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction

Chunan Liu, Lilian Denzler, Yihong Chen +2

Epitope identification is vital for antibody design yet challenging due to the inherent variability in antibodies. While many deep learning methods have been developed for general…

cs.CL2024

Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language

Jiayi Wang, Yao Lu, Maurice Weber +4

English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs s…