“Ah didn't realize you were referring to NoPE explicitly. And yea, the intuitions gained from that paper are pretty much what I alluded to above, you don't get away with never modeling the positional data, the question is how you model it effectively and from where do you derive that signal. NoPE never really took off more broadly in modern architecture i…”
按年被提到
20242025 · 2 次2026
Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings
Chunsheng Zuo, Pavel Guerzhoy, Michael Guerzhoy · 2024
被提及 · 2 人首次 2025-01-25 · 最近 2025-07-30
2不同的人
2活跃月份
2讨论串
0被引(OpenAlex)
arXiv 摘要(候选层不写导读)
Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis about how positional information can be stored without using explicit positional encoding. We observe that nearby embeddings are more similar to each other than faraway embeddings, allowing the transformer to potentially reconstruct the positions of tokens. We show that this pattern can occur in both the trained and the randomly initialized Transformer models with causal attention and no positional encodings over a common range of hyperparameters.
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spmurrayzzz · 2025-07
被提交为 story · 1 次
- Position Information Emerges in Causal Transformers Without Positional Encoding ↗PaulHoule · 2025-01-25 · 3 分