4836 位用户此时在线
24小时点击排行 Top 10：
- 本站自动实时分享网络热点
- 24小时实时更新
- 所有言论不代表本站态度
- 欢迎对信息踊跃评论评分
- 评分越高，信息越新，排列越靠前
搜索数据不够精准？ 请点击上面👆👆👆其它时间段筛选试试吧！
1
I've verified from reliable sources. New visual Turing Test: this is a real robot demo! The controller is a neural net trained in Isaac simulator using reinforcement learning and then sim2real. Reward engineering is all you need.
2
1
1
I've verified from reliable sources. New visual Turing Test: this is a real robot demo! The controller is a neural net trained in Isaac simulator using reinforcement learning and then sim2real. Reward engineering is all you need.
Walking gait's got swag but we need these robots
时政
(
twitter.com)
00:00:06
2
The most epic AI panel in a while! We at NVIDIA have gathered ALL 8 authors of "Attention is All You Need" for a panel at GTC, hosted by none other than the GOAT himself, Jensen Huang.
2
1
1
The most epic AI panel in a while! We at NVIDIA have gathered ALL 8 authors of "Attention is All You Need" for a panel at GTC, hosted by none other than the GOAT himself, Jensen Huang.
In 2017, 8 researchers had a flash of genius and invented Transformer, the seminal work that…
时政
(
twitter.com)
•
Jim Fan
3
If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all…
2
1
1
If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all…
时政
(
twitter.com)
00:00:15
4
4
3
3
5
2
1
1
6
So many announcements today. Meta just dropped EmuVideo, generating 4-second short videos at 512x512 resolution and 16 FPS. Idea is quite straightforward: text -> image first, then do a "super-resolution" of the image along the temporal axis to synthesize motion.
2
1
1
So many announcements today. Meta just dropped EmuVideo, generating 4-second short videos at 512x512 resolution and 16 FPS. Idea is quite straightforward: text -> image first, then do a "super-resolution" of the image along the temporal axis to synthesize motion.
Long-form…
时政
(
twitter.com)
00:00:07
7
Here's why DALLE 3, once deployed, will improve at a faster rate than MidJourney:
3
2
2
Here's why DALLE 3, once deployed, will improve at a faster rate than MidJourney:
1. Multi-turn dialogue is an excellent UI to collect human feedback. People will explain what's wrong with the generated image in free-form language, giving very fine-grained annotations for each…
时政
(
twitter.com)
•
Jim Fan
8
2
1
1
9
Autonomous driving with Chain of Thought - autopilot thinking out loud in text!
2
1
1
Autonomous driving with Chain of Thought - autopilot thinking out loud in text!
LINGO-1 is the most interesting work I've read in autodriving for a while.
Before: perception -> driving action
After: perception -> textual reasoning -> action
LINGO-1 trains a video-language…
时政
(
twitter.com)
00:00:35
10
This is "Sequential Dexterity", a neural network that controls a robot arm to build legos given a manual 🤖
2
1
1
This is "Sequential Dexterity", a neural network that controls a robot arm to build legos given a manual 🤖
To do this task, the robot needs to chain together multiple skills (grasping, re-orienting, pushing, etc.) and execute without compounding error.
I find some very simple…
时政
(
twitter.com)
00:00:46
11
2
1
1
12
This is an ape ("Kanzi") playing Minecraft! A fascinating experiment on non-human biological neural networks 🙉
3
2
2
This is an ape ("Kanzi") playing Minecraft! A fascinating experiment on non-human biological neural networks 🙉
I've been teaching AI to play Minecraft for too long. There're so many similar techniques that the ape trainers used:
- In-context reinforcement learning: Kanzi gets…
时政
(
twitter.com)
00:03:01