For agents to improve over time, they can’t afford to forget what they’ve already mastered.
We found that supervised fine-tuning forgets more than RL when training on a new task!
Want to find out why? 👇
We have a fun collaboration of @GPU_MODE x @scaleml coming up!
We’re hosting a week-long online bootcamp that explores the core components of GPT-OSS while also diving into cutting-edge research that pushes beyond what’s currently in GPT-OSS!
For example, how can MoE's power…
Happy to announce that we’ll be presenting our work on sim-and-real cotraining at IROS 2025!
Check out our latest arXiv version - we’ve added new experiments for 2 alternative co-training formulations and addressed some FAQs
📄 arxiv.org/abs/2503.22634
🌐 sim-and-real-cotraining.github.io
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…
Announcing Ambient Diffusion Omni — a framework that uses synthetic, low-quality, and out-of-distribution data to improve diffusion models.
State-of-the-art ImageNet performance. A strong text-to-image results in just 2 days on 8 GPUs.
Filtering ❌
Clever data use ✅
What if an LLM could update its own weights?
Meet SEAL🦭: a framework where LLMs generate their own training data (self-edits) to update their weights in response to new inputs.
Self-editing is learned via RL, using the updated model’s downstream performance as reward.
We're really honored to be named alongside Ajay and Justin for this award, from the hands-down best technical committee in robotics!
Here's the paper arxiv.org/abs/2304.11259 and accompanying video youtube.com/watch?v=L57Jz3…
We're really honored to be named alongside Ajay and Justin for this award, from the hands-down best technical committee in robotics!
Here's the paper arxiv.org/abs/2304.11259 and accompanying video youtube.com/watch?v=L57Jz3…
Amazing concurrent work showing the effectiveness of sim+real cotraining on a wide range of tasks! The similarity of our findings suggests that sim data could unlock massive improvements in robotics... I'm excited to see what comes next in this space
Amazing concurrent work showing the effectiveness of sim+real cotraining on a wide range of tasks! The similarity of our findings suggests that sim data could unlock massive improvements in robotics... I'm excited to see what comes next in this space
2K Followers 2K FollowingAssistant professor in computer science, University of Toronto | @UofTRobotics @VectorInst | Working on robotics, vision, and machine learning.
7K Followers 543 FollowingAssistant Professor of Computer Science @Columbia @ColumbiaCompSci, Postdoc from @Stanford @StanfordSVL, PhD from @MIT_CSAIL. #Robotics #Vision #Learning
23 Followers 5K FollowingLike to try new things you never know; trying to prove all software can be automated 😅 😅 😅
| ML/AI, | C++/Java/Go |
GitHub : Dyl777
44 Followers 1K Following#NLProc PhD LORIA/CNRS/Université de Lorraine, I work on generation of questions, from structured and unstructured data. https://t.co/3mUSCnSHTf
136 Followers 3K Followingالدنيا كلها جهل، الّا مواضع العلم
والعلم كله جهل، الّا ما عُمِل به
والعمَل كله رياء، الّا ما كان مخلصاً
والاخلاص على خطَر، حتى ينظرَ العبد بما يُختم له
9K Followers 874 FollowingAssistant Professor at University of Washington. I like robots, and reinforcement learning. Previously: post-doc at MIT, PhD at Berkeley
2K Followers 2K FollowingAssistant professor in computer science, University of Toronto | @UofTRobotics @VectorInst | Working on robotics, vision, and machine learning.
9K Followers 874 FollowingAssistant Professor at University of Washington. I like robots, and reinforcement learning. Previously: post-doc at MIT, PhD at Berkeley
1K Followers 105 FollowingAssistant Professor @mldcmu. Formerly: Postdoc @MITEECS, PhD @Berkeley_EECS, Math Undergrad @Princeton. New to Twitter. https://t.co/67bMOAyqK6
85K Followers 306 FollowingHigh performance civilian robot manufacturer.
Please everyone be sure to use the robot in a Friendly and Safe manner.
https://t.co/hI6LafokVm
7K Followers 6K FollowingProduct Lead | Google Gemini
Prev: Launched @aws Trainium, @alexa99 Echo Show 5
Tweets are my own. Retweets are not endorsements.
Joyful Learning Machines
3K Followers 616 FollowingTrying to understand the emergence of generally intelligent robotic behavior at @berkeley_ai @AIatMeta. Previously @CILVRatNYU @MIT & @Apple AI/ML fellow.
7K Followers 543 FollowingAssistant Professor of Computer Science @Columbia @ColumbiaCompSci, Postdoc from @Stanford @StanfordSVL, PhD from @MIT_CSAIL. #Robotics #Vision #Learning