← Search

Shenghu Jiang

2 accepted papers

2026

Incremental BPE Tokenization

ICML 2026spotlight

We propose a novel algorithm for incremental Byte Pair Encoding (BPE) tokenization. The algorithm processes each input byte in **worst-case** $\mathcal{O}(\log^2 t)$ time, leading to an overall complexity of $\mathcal{O}(n \log^2 t)$, where $n$ is the input length and $t$ is the maximum token length…

Cited by 0SourceScholar
2019

Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks

ICCV 2019poster

Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on resource-limited devices like mobile phones. However, due to the discreten…

Cited by 591PDFScholar