Picture

Nathan Ratliff @robot_trainer

Director of Robotic Systems @NVIDIA. Isaac Cortex, cobots, geometric methods; PhD CMU, research Max Planck, TTI-C, co-founder Lula Robotics, eng Google, Amazon linkedin.com/in/nathan-ratl… Seattle, WA Joined December 2010
  • Tweets
    518
  • Followers
    2K
  • Following
    380
  • Likes
    2K
Nathan Ratliff retweeted
andrewgwils Profile Picture

Andrew Gordon Wilson @andrewgwils

4 weeks ago

Regardless of whether you plan to use them in applications, everyone should learn about Gaussian processes, and Bayesian methods. They provide a foundation for reasoning about model construction and all sorts of deep learning behaviour that would otherwise appear mysterious.

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

a month ago

hehehe

TheHumanoidHub Profile Picture

The Humanoid Hub @TheHumanoidHub

a month ago

hehehe

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

a month ago

😮🫤🤪🫥🤖

rohanpaul_ai Profile Picture

Rohan Paul @rohanpaul_ai

a month ago

😮🫤🤪🫥🤖

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

make sure you expert makes mistakes and has to explore. there's been a lot of work around ensuring demonstrators have the same information as the robot, but this works shows it's super useful for the demonstrator to have less! super interesting.

AvivTamar1 Profile Picture

Aviv Tamar @AvivTamar1

2 months ago

make sure you expert makes mistakes and has to explore. there's been a lot of work around ensuring demonstrators have the same information as the robot, but this works shows it's super useful for the demonstrator to have less! super interesting.

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

andrew's explanations are always lucid and insightful. recommend taking a look. deep nets have soft (but flexible) inductive biases preferring simple explanations, and they're able to characterize that rigorously pulling out some decades old theory. super cool.

andrewgwils Profile Picture

Andrew Gordon Wilson @andrewgwils

2 months ago

andrew's explanations are always lucid and insightful. recommend taking a look. deep nets have soft (but flexible) inductive biases preferring simple explanations, and they're able to characterize that rigorously pulling out some decades old theory. super cool.

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

hehe

ChrSzegedy Profile Picture

Christian Szegedy @ChrSzegedy

2 months ago

hehe

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

science

RussTedrake Profile Picture

Russ Tedrake @RussTedrake

2 months ago

science

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

good points. openai created llms at scale well before chatgpt, but chatgpt made them accessible and that was arguably more impactful. all the recent models have been technically spectacular, but making them universally accessible may again be felt (significantly) more strongly by…

kimmonismus Profile Picture

Chubby♨️ @kimmonismus

2 months ago

good points. openai created llms at scale well before chatgpt, but chatgpt made them accessible and that was arguably more impactful. all the recent models have been technically spectacular, but making them universally accessible may again be felt (significantly) more strongly by…

Nathan Ratliff retweeted
NandoDF Profile Picture

Nando de Freitas @NandoDF

2 months ago

It is remarkable that a committee of deliberating AI models can diagnose patients, propose the next tests, use the results of the tests to improve the diagnosis, order more tests, and eventually arrive at diagnoses, outperforming doctors. It is a specific setting, but nonetheless…

mustafasuleyman Profile Picture

Mustafa Suleyman @mustafasuleyman

2 months ago

It is remarkable that a committee of deliberating AI models can diagnose patients, propose the next tests, use the results of the tests to improve the diagnosis, order more tests, and eventually arrive at diagnoses, outperforming doctors. It is a specific setting, but nonetheless…

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

weird thought. ice doesn't cool, it sucks in heat. and it does it by starting as this pristine organized lattice, and letting the overly energetic particles around it beat it to a pulp. it's a punching bag for hyper molecules. huh

robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

ok guys, we got 12 years to turn all the road's cars autonomous. my oldest will want his learners permit then, and I want that problem to just be not a thing anymore :) also, I've actually done the 15 hrs on the road before, and that's gonna be my "back in the day" story!

niccruzpatane Profile Picture

Nic Cruz Patane @niccruzpatane

2 months ago

ok guys, we got 12 years to turn all the road's cars autonomous. my oldest will want his learners permit then, and I want that problem to just be not a thing anymore :) also, I've actually done the 15 hrs on the road before, and that's gonna be my "back in the day" story!

Trends for United States

Tylenol
22,5 B posts
#2KDay
75,5 B posts
Alcaraz
52,4 B posts
Department of War
87,9 B posts
#CashAppFriday
8.443 posts
Ryan Clark
6.114 posts
Djokovic
47,1 B posts
Hyundai
102 B posts
S&P 500
15,4 B posts
Free Angel
1.317 posts
$HOOD
16,2 B posts
Chargers
29,4 B posts
Chargers
29,4 B posts
#SmackDown
18,2 B posts
Eric Adams
10,5 B posts
#2kgiveaway
57,8 B posts
Eswatini
6.535 posts
Rosie
36,9 B posts
#YIAY2025
Sorber

You might like

Research Scientist @GoogleDeepMind working on foundation models for robotics. PhD @CMU_Robotics @iamlab_cmu
Jacky Liang
@jackyliang42
6K Followers
Prof @Stanford, Distinguished Research Scientist and AV research lead @nvidia. PhD from @MITAeroAstro. Robotics, autonomous systems, AI. Opinions are my own.
Marco Pavone
@drmapavone
4K Followers
Associate Prof. @Cambridge_Uni in ML/AI + Robotics | earlier: @Stanford Postdoc, @kth_rpl PhD, @CMU_Robotics MS, @Google engineer (search, OCR+Books/StreetView)
Rika Antonova
@contactrika
2K Followers
Associate Professor in Robotics @Princeton. 20% Research Scientist @GoogleDeepMind in Princeton.
Anirudha Majumdar
@Majumdar_Ani
6K Followers
Mostly posting about robots. currently AI @agilityrobotics prev embodied AI @AIatMeta, @NVIDIAAI. All views my own. writing: https://t.co/iNLA4djfZo
Chris Paxton
@chris_j_paxton
19K Followers
Roboticist; Assistant Professor of @NAMEatUM, University of Michigan Director of Computational Autonomy and Robotics Laboratory
Maani Ghaffari
@GhaffariMaani
4K Followers
Postdoc at @UMontreal & @Mila_Quebec in causal learning for robots and embodied AI. Prior stops at @CMU_Robotics, @nvidia, LM Space ATC, & Uber ATG.
Tabitha Edith Lee
@TabulaRobot
929 Followers
Research Scientist at @AIatMeta (FAIR). Embodied AI. Prev: @DFKI, @TUDarmstadt, @NvidiaAI. https://t.co/RQpq7Prbln X https://t.co/umZQeDjJv4
Julen Urain
@robotgradient
984 Followers
Building Human-embodied Intelligence. CEO @MyoLabAI, Ad. Prof. @CMU_Robotic | Sr. research scientist @OpenAI @GoogleAI @AIatMeta | @berkeley_ai @UWcse #MuJoCo
Vikash Kumar
@Vikashplus
5K Followers
Professor @CS_TUDarmstadt, @hessian_AI, AI Emmy Noether @dfg_public, #ERCStG SIREN, co-chair TC @MobileManip & chair WiE @ieeeras
Georgia Chalvatzaki
@GeorgiaChal
6K Followers
Sr. Research Scientist at @NVIDIAAI. Foundation models for robotics. Previously PhD at @CMU_Robotics, @Berkeley_EECS, @MetaAI, AWS
Adithya Murali
@Adithya_Murali_
2K Followers
Researching reasoning @OpenAI | Co-created Libratus/Pluribus superhuman poker AIs, CICERO Diplomacy AI, and OpenAI o3 / o1 / 🍓 reasoning models
Noam Brown
@polynoamial
91K Followers
https://t.co/2usZLzRs4A
Dimitri Bertsekas
@DBertsekas
11K Followers
#RobotLearning Professor (#MachineLearning #Robotics) at @ias_tudarmstadt of @TUDarmstadt (Part of @ELLISforEurope, @Hessian_AI and @DFKI)
Jan Peters
@Jan_R_Peters
5K Followers
Assistant Professor at University of Washington. I like robots, and reinforcement learning. Previously: post-doc at MIT, PhD at Berkeley
Abhishek Gupta
@abhishekunique7
9K Followers