按年被提到
20232023 · 3 次2026
视觉、语音与图像生成›语音与音频生成·arXiv:2306.00238 · cs.CV

Bytes Are All You Need: Transformers Operating Directly On File Bytes

Maxwell Horton, Sachin Mehta, Ali Farhadi, Mohammad Rastegari · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2023-06-02 · 最近 2026-06-20
4不同的人
2活跃月份
4讨论串
4被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Modern deep learning approaches usually utilize modality-specific processing. For example, the most common deep learning approach to image classification involves decoding image file bytes into an RGB tensor which is passed into a neural network. Instead, we investigate modality-independent representation learning by performing classification directly on file bytes, without the need for decoding files at inference time. This enables models to operate on various modalities without any hand-designed, modality-specific processing. Our model, ByteFormer, improves ImageNet Top-1 classification accuracy by $5\%$ (from $72.2\%$ to $77.33\%$) relative to DeIT models of similar size. Compared to Perceiver IO, our model requires absolutely no modality-specific processing at inference time, and uses an order of magnitude fewer parameters at equivalent accuracy on ImageNet. We demonstrate that the same ByteFormer architecture can perform audio classification without modifications or modality-specific preprocessing. We achieve $95.42\%$ classification accuracy on the Speech Commands V2 dataset (comparable to the state-of-the-art accuracy of $98.7\%$). Additionally, we demonstrate that ByteFormer can operate jointly on images and audio, handling joint classification without explicit knowledge of the input modality. We release our code at https://github.com/apple/corenet/tree/main/projects/byteformer.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论woadwarrior01 · 2026-06

“There are many approaches around this, the simplest being to treat bytes as tokens (cf: Google's ByT5[1]). Also, BLT[2] from Meta and ByteFormer[3] from Apple. [1]: https://arxiv.org/abs/2105.13626 [2]: https://arxiv.org/abs/2412.09871 [3]: https://arxiv.org/abs/2306.00238”

Data Compression Explained原评论 ↗
被提交为 story · 3 次