Nishanth Kumar
@nishanthkumar23
AI/ML + Robots PhD Student @MIT_LISLab, intern @AIatMeta. Formerly @NVIDIAAI, @rai_inst, @brownbigai, @vicariousai and @uber.
You might like
World models hold a lot of promise for robotics, but they're data hungry and often struggle with long horizons. We learn models from a few (< 10) human demos that enable a robot to plan in completely novel scenes! Our key idea is to model *symbols* not pixels 👇
Full episode dropping soon! Geeking out with @nishanthkumar23 on From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models pix2pred.csail.mit.edu Co-hosted by @micoolcho @chris_j_paxton
I had a fun time chatting about new work on symbolic world model learning with @chris_j_paxton and @micoolcho on robopapers recently! Check it out if you’d like to hear about all the fruit we used up getting the robot to operate a juicer :)
Full episode dropping soon! Geeking out with @nishanthkumar23 on From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models pix2pred.csail.mit.edu Co-hosted by @micoolcho @chris_j_paxton
The robot demo videos continue to improve! I thought segments of this were from sim for a while based on how good the movement looked + how long the task horizons are 🤯
Today, we present a step-change in robotic AI @sundayrobotics. Introducing ACT-1: A frontier robot foundation model trained on zero robot data. - Ultra long-horizon tasks - Zero-shot generalization - Advanced dexterity 🧵->
Very interesting and cool stuff! This is perhaps the most compelling evidence so far that scaling data with the right architectures might take us very far towards general purpose dexterous manipulation. Excited to read more details and understand how harmonic reasoning works 🤖
Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇
Our lab is hiring a postdoc! Reach out if you want to push the frontiers of robot learning from human data.
For people interested in learning more about this work, my wonderful advisor Leslie Kaelbling gave a keynote at @RL_Conference recently where she discussed this paper + how it fits into a broader framework for general-purpose robotics! Watch the talk here:…
youtube.com
YouTube
Leslie Kaelbling - RL: Rational Learning
World models hold a lot of promise for robotics, but they're data hungry and often struggle with long horizons. We learn models from a few (< 10) human demos that enable a robot to plan in completely novel scenes! Our key idea is to model *symbols* not pixels 👇
Check out Leslie Kaelbling's #RLC2025 Keynote where she talks about some new pespectives and a number of new works from the group: youtube.com/watch?v=10OjAI…
youtube.com
YouTube
Leslie Kaelbling, RL: Rational Learning - RLC 2025
This is my new favorite robot demo video - very impressive! Expert level table tennis seems more within reach than I would have thought!
We're excited for #RLC2025! If you're at the conference, be sure to catch our PI Leslie Kaelbling's keynote on "RL: Rational Learning" from 9-10 in CCIS 1-430. Leslie will talk about some new perspectives + exciting new results from the group: you won't want to miss it! 🤖
I competed on robotics teams (FIRST, WRO) throughout middle and high school and loved it. When I got to college, I asked @StefanieTellex about forming an undergrad robotics competition club. She suggested I try research first. “Research is cooler”, she said. She was right!
📢 Excited to announce the 1st workshop on Making Sense of Data in Robotics @corl_conf! #CORL2025 What makes robot learning data “good”? We focus on: 🧩 Data Composition 🧹 Data Curation 💡 Data Interpretability 📅 Papers due: 08/22/2025 🌐 tinyurl.com/corldata25 🧵(1/3)
United States Trends
- 1. $ENLV 5,049 posts
- 2. #IDontWantToOverreactBUT N/A
- 3. #GEAT_NEWS N/A
- 4. Jimmy Cliff 14.4K posts
- 5. #MondayMotivation 10.9K posts
- 6. Good Monday 43.7K posts
- 7. Thanksgiving 132K posts
- 8. Victory Monday 2,785 posts
- 9. $GEAT N/A
- 10. TOP CALL 4,403 posts
- 11. #VenezuelaVictoriaTotal 2,159 posts
- 12. DOGE 211K posts
- 13. The Harder They Come 1,792 posts
- 14. Shane Bowen 6,871 posts
- 15. Monad 151K posts
- 16. #MondayVibes 2,915 posts
- 17. AI Alert 2,313 posts
- 18. $NVO 2,890 posts
- 19. $OSCR 2,690 posts
- 20. Soles 89.4K posts
You might like
-
David Held
@davheld -
Abhishek Gupta
@abhishekunique7 -
Danfei Xu
@danfei_xu -
Ofir Nachum
@ofirnachum -
Archit Sharma
@archit_sharma97 -
Deepak Pathak
@pathak2206 -
Rishabh Agarwal
@agarwl_ -
Animesh Garg
@animesh_garg -
Pulkit Agrawal
@pulkitology -
Oier Mees
@oier_mees -
bigAI
@BrownBigAI -
Andy Zeng
@andyzengineer -
Learning and Intelligent Systems (LIS) @ MIT
@MIT_LISLab -
Lerrel Pinto
@LerrelPinto -
Vikash Kumar
@Vikashplus
Something went wrong.
Something went wrong.