Xiuqi Yang — accepted AI-conference papers

2025

E-Verify: A Paradigm Shift to Scalable Embedding-based Factuality Verification

Zeyang Liu, Jingfeng Xue, Xiuqi Yang, Wenbiao Du, Jiarun Fu, Junbao Chen +2

EMNLP 2025

Large language models (LLMs) exhibit remarkable text-generation capabilities, yet struggle with factual consistency, motivating growing interest in factuality verification. Existing factuality verification methods typically follow a Decompose-Then-Verify paradigm, which improves granularity but suff

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2020

Towards Unified INT8 Training for Convolutional Neural Network

Feng Zhu, Ruihao Gong, Fengwei Yu, Xianglong Liu, Yanfei Wang, Zhelong Li +2

CVPR 2020poster

Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can further bring more considerable acceleration, since the backward process is often computation-intensive. Unfortunately, the i…

Cited by 218 PDF ↗Scholar ↗