2 citations · 2 across the 2 of their papers we have counts for
7 papers
Theoretical Benefit and Limitation of Diffusion Language Model
Guhao Feng, Yihan Geng, Jian Guan +3
Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models…
How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
Guhao Feng, Kai Yang, Yuntian Gu +6
Despite the remarkable success of Transformer-based large language models (LLMs) across various domains, understanding and enhancing their mathematical capabilities remains a signi…
Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses
Haojun Yu, Youcheng Li, Nan Zhang +17
Data-driven deep learning models have shown great capabilities to assist radiologists in breast ultrasound (US) diagnoses. However, their effectiveness is limited by the long-tail…
Do Efficient Transformers Really Save Computation?
Kai Yang, Jan Ackermann, Zhenyu He +6
As transformer-based language models are trained on increasingly large datasets and with vast numbers of parameters, finding more efficient alternatives to the standard Transformer…
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
Bohang Zhang, Jingchu Gai, Yiheng Du +3
Designing expressive Graph Neural Networks (GNNs) is a fundamental topic in the graph learning community. So far, GNN expressiveness has been primarily assessed via the Weisfeiler-…
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
Zhenyu He, Guhao Feng, Shengjie Luo +6
In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position,…