思想与社会2023 · 分享于 Hacker News
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
探索《Mamba: Linear-Time Sequence Modeling with Selective State Spaces》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Ytodsacerdoti ·
Our next-generation model: Gemini 1.5
1,244 赞同588 评论
Ymarc__1 ·
Claude 3 model family
1,016 赞同683 评论
YPhilpax ·
GPT-5: Key characteristics, pricing and system card
643 赞同295 评论
Ybeefman ·
Were RNNs all we needed?
520 赞同260 评论
Ytosh ·
Codestral Mamba
485 赞同138 评论
YLaserPineapple ·
Understand how transformers work by demystifying the math behind them
470 赞同137 评论
Yguybedo ·
Eagle 7B: Soaring past Transformers
400 赞同81 评论
Ygnyeki ·
My Python code is a neural network
331 赞同67 评论
Yjackcook ·
Mamba: The Easy Way
279 赞同60 评论
Yyuhongsun ·
Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data
231 赞同129 评论
Ytaiboku256 ·
Ask HN: Is anybody building an alternative transformer?
148 赞同93 评论
Yjulius ·
A pure NumPy implementation of Mamba
100 赞同35 评论
YByteAtATime ·
Cerebras achieves 2,500T/s on Llama 4 Maverick (400B)
93 赞同93 评论
Ymilliondreams ·
Generative AI and the big buzz about small language models
13 赞同5 评论
Ymatt_d ·
FlashAttention-T: Towards Tensorized Attention
12 赞同0 评论
Ybehnamoh ·
Mamba outperforms transformers "everywhere we tried"
7 赞同0 评论
YMAXPOOL ·
Introduction to State Space Models (SSM)
4 赞同1 评论
Yjohnma2006 ·
Minimal implementation of Mamba, the new LLM architecture, in 1 file of PyTorch
3 赞同0 评论
Yanigbrowl ·
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
2 赞同0 评论
Ykvee ·
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
1 赞同0 评论
Yxenova ·
Mamba: New SSM arch with linear-time scaling that outperforms Transformers
1 赞同1 评论
Yhahnchen ·
Ask HN: AI/ML papers to catch up with current state of AI?
1 赞同0 评论