Skip to content

少有的同时做过 Agent、多模态和具身的人 | 对谈前混元多模态 RL Infra 负责人淏楠

October 24, 2026 · 54 min

Show notes

这期的嘉宾淏楠非常「折腾」。他读过五个大学,读着觉得没意思就换,也是少有的同时做过 Agent、多模态、RL 和具身的人,而且总是做一些逆势而为(非主流)的选择:
他曾在陈天桥和代季峰两位老师的 MiroMind 工作,是最早一批做 Agent 的人,却在 Agent 最热的时候放弃更丰厚的 package,转向多模态。在混元负责多模态 RL infra、主导推出开源多模态强化学习框架 UniRL 之后,他最近又换了方向,去了一家具身公司负责模型训练。其实,Astra 的出现给具身行业带来了不小的震动,也似乎抹平了各家此前在「大脑」上积累的优势。淏楠在此时入局,总有那么一丝「49 年加入国军」的意味。
不过,这些选择看似很跳,但背后的思考一脉相承,既关乎个人志趣,也有对技术发展和未来空间的判断。所以从 Agent 到多模态再到具身,一路做下来,淏楠收获了什么?这几个方向的实际进展,与外界的...去小宇宙查看完整单集简介
在小宇宙查看该单集文稿

All episodes of 42章经

Settings

Display

Language

Decides which stations you see first on the home page.

History

Recently played stations and episodes and your latest searches are only stored in this browser.

Notifications

A short notice when a podcast you follow has a new episode. Turn off single podcasts with the bell on their page.

Account

Save favorites – in the app and on the website.

Keyboard shortcuts

/
Open search
Space
Play or pause
← →
In the player: back 15 s, forward 30 s (episodes) · in a row: next tile
↑ ↓
In a row: target within the tile
Home / End
In a row: first or last tile
Esc
Close window or menu
?
This overview
Now playing

Go to station page

Play next

    Add episodes with “Play next” – they play after the current episode.