sandip k @sdkTwitting

Washington DC Joined March 2011

Tweets

13
Followers

34
Following

221
Likes

56

Yann LeCun @ylecun

2 years ago

@DrJimFan @RichardSSutton Animals and humans get very smart very quickly with vastly smaller amounts of training data. My money is on new architectures that would learn as efficiently as animals and humans. Using more data (synthetic or not) is a temporary stopgap made necessary by the limitations of our…

315 577 5K 3.0M 970

Tim Ferriss @tferriss

2 years ago

In 1992, I was 15 years old and had landed in Japan for my first extended trip abroad. I would be an exchange student at Seikei Gakuen high school for one year. On the first day of classes, I reported to the faculty lounge in my required navy-blue uniform, looking like a West…

50 106 1K 278K 385

Yam Peleg @Yampeleg

2 years ago

You thought XGBoost was powerful enough? Introducing: XGBoost 2. - Multi-target trees (vector-leafs) - Finally: 𝚍𝚎𝚟𝚒𝚌𝚎 parameter. - 𝚊𝚙𝚙𝚛𝚘𝚡 for GPU devices. - Controllable histogram bound (to optimize RAM) - Batch by batch training (External Memory) - Learning to…

15 120 867 141K 354

Google DeepMind @GoogleDeepMind

2 years ago

Introducing 𝗥𝗧-𝗫: a generalist AI model to help advance how robots can learn new skills. 🤖 To train it, we partnered with 33 academic labs across the world to build a new dataset with experiences gained from 22 different robot types. Find out more: dpmd.ai/TW_RT-X

25 307 1K 519K 278

Download Gif

Ari Seff @ari_seff

2 years ago

Can we model driving similarly to how we model language? Excited to introduce MotionLM, where we represent driving scenarios as conversations among road users. It establishes a new state-of-the-art in multi-agent motion forecasting: arxiv.org/abs/2309.16534

13 112 881 176K 468

Download Gif

Aran Komatsuzaki @arankomatsuzaki

2 years ago

Representation Engineering: A Top-Down Approach to AI Transparency Identifies and characterizes the emerging area of representation engineering, an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience arxiv.org/abs/2310.01405

2 61 414 344K 399

Download Image

sandip k @sdkTwitting

2 years ago

I just travelled 1428 meters into the frantic mines of @RailRush on iOS! Can you top it? bit.ly/QA1dtV

0 0 0 21 0

nature @Nature

4 years ago

A rigorous study based on a randomized trial finds that surgical masks are highly protective against the spread of COVID-19, but cloth masks fall short. go.nature.com/3tq9CaK