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
😮🫤🤪🫥🤖
MASSIVE claim in this paper. AI Architectural breakthroughs can be scaled computationally, transforming research progress from a human-limited to a computation-scalable process. So it turns architecture discovery into a compute‑bound process, opening a path to…
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.
Want robot imitation learning to generalize to new tasks? Blindfold your human demonstrator! Best robotics paper at EXAIT Workshop #ICML2025 openreview.net/forum?id=zqfT2… Wait, why does this make sense? Read below!
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.
Excited to be presenting my paper "Deep Learning is Not So Mysterious or Different" tomorrow at ICML, 11 am - 1:30 pm, East Exhibition Hall A-B, E-500. I made a little video overview as part of the ICML process (viewable from Chrome): recorder-v3.slideslive.com/#/share?share=…
science
TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the…
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…
A brief overview of GPT-5 GPT-5 could disappoint some and amaze many. It's a strange contradiction, but I'll try to explain. For “hardcore” users, GPT-5 will be a bit of a disappointment, if the rumors are to be believed. Rumor has it that Sam Altman is not particularly…
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…
Microsoft AI built MAI-DxO to simulate a virtual panel of physicians with different approaches collaborating to find a diagnosis on each case. They also included the ability to set a budget to avoid infinite testing (higher costs, longer wait times, etc.).
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
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!
Calling it a day after almost 15 hours on the road and close to 900 miles. I would NEVER in a million years be able to drive this long and far without FSD. Massive game changer for me. Like I said before, FSD is a IRL cheat code.
I've found industry to be more rigorous with statistics and experimentation because of resourcing, and obviously it's bleeding edge in ai right now. that said, it can be tough digging out of a lower profile job and takes a certain personality to do so. it's not a shame to want or…
You don’t need a PhD to be a great AI researcher. Even @OpenAI’s Chief Research Officer doesn’t have a PhD.