Fei-Fei Li(@drfeifei)
I’m very excited by this test time training work for robotic learning! It’s an awesome collaboration...
6.4内容质量

TL;DR · AI 摘要
Fei-Fei Li on X: "I’m very excited by this test time training work for robotic learning! It’s an awesome collaboration b...
核心要点
- 主题聚焦:I’m very excited by this test time training work
- 来源:Fei-Fei Li(@drfeifei),建议结合原文判断细节。
- AI 分析暂不可用,本条为保底评分与摘要。
#AI
打开原文Fei-Fei Li on X: "I’m very excited by this test time training work for robotic learning! It’s an awesome collaboration between @StanfordSVL and @NVIDIARobotics !" / X
Fei-Fei Li
@drfeifei
I’m very excited by this test time training work for robotic learning! It’s an awesome collaboration between
@
StanfordSVL
and
NVIDIARobotics
!
Jim Fan
@DrJimFan
15h
We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude
Show more
00:00
8:55 PM · Jul 15, 2026
39.4K
Views
7
2
1
21
9
199
5
6
56
Read 7 replies