注册并分享邀请链接,可获得视频播放与邀请奖励。

Shivam Duggal
@ShivamDuggal4
PhD Student @MIT | Prev: Carnegie Mellon University @SCSatCMU | Research Scientist @UberATG
加入 June 2017
455 正在关注    1.6K 粉丝
Language models process each token through a single residual stream (blue arrows): reading / writing memory and applying MLPs at each layer, and finally decoding the next token. Can we scale up this single stream computation? Introducing Latent Lattice Language Models (LLLMs): augmenting this vertical stream with a horizontal axis of computation—the Lattice of Latents (orange arrows). RNN 🤝 Transformers 🧵
显示更多
0
17
364
59
转发到社区