Nishanth Kumar
@nishanthkumar23
Followers
1K
Following
10K
Media
23
Statuses
285
Robotics + AI PhD Student @MIT_LISLab @MIT_CSAIL. Formerly @NVIDIAAI @rai_inst, @brownbigai, @vicariousai and @uber. S.B @BrownUniversity.
Cambridge, MA
Joined July 2015
Can we get robots to improve at long-horizon tasks without supervision?. Our latest work tackles this problem by planning to practice!. Here's a teaser showing initial task -> autonomous practice -> eval (+ interference by a gremlinšæ)
1
18
114
RT @siddkaramcheti: Thrilled to share that I'll be starting as an Assistant Professor at Georgia Tech (@ICatGT / @GTrobotics / @mlatgt) inā¦.
0
25
0
It was a ton of fun to help @WillShenSaysHi and @CaelanGarrett on new work that does GPU-accelerated TAMP! Exciting progress towards . efficient test time scaling for robots š¤.
Check out this MIT News article about our research on GPU-accelerated manipulation planning! @WillShenSaysHi @nishanthkumar23 @imankitgoyal.
0
1
7
This has to be one of the coolest robot demo videos Iāve seen! Very impressive stuff from @physical_int.
Ļ-0.5 is here, and it can generalize to new homes! Some fun experiments with my colleagues at @physical_int, introducing Ļ-0.5 (āpi oh fiveā). Our new VLA can put dishes in the sink, clean up spills and do all this in homes that it was not trained inš§µš
1
1
30
Very interesting new work (that builds on our work on planning to practice!) on open ended learning and exploration for LLM agents! In general Iām quite excited for ideas from planning, RL, and Robotics to help make LLM agents even more autonomous and capable! š¤.
š Introducing š§MAGELLANāour new metacognitive framework for LLM agents! It predicts its own learning progress (LP) in vast natural language goal spaces, enabling efficient exploration of complex domains.šāØLearn more: š #OpenEndedLearning #LLM #RL.
0
0
3
Iām at #AAAI2025 for the next two days! Come say hi in todayās āPlanning in the era of LLMsā or the āGenPlanā workshops. Also keen to chat about any and all things related to test time scaling via search, robotics, agents, or food in Philly!.
1
1
12
0
3
0
Iām quite biased, but I think this is some cool and interesting work on using LLMs for robotics :).
Can we teach a robot its limits to do chores safely & correctly? š§µ. To help robots execute open-ended, multi-step tasks, MIT CSAIL researchers used vision models to see whatās near the machine & model its constraints. An LLM sketches up a plan thatās checked in a simulator to
0
3
32
RT @wenlong_huang: Excited to share that ReKep won Best Paper Award at CoRL LEAP workshop!. Extracting plannable task representations fromā¦.
0
11
0
Happening in a few hours (4pm in the main auditorium Audimax!).
Curious to hear about creating generalist robots from leaders in the field? Donāt miss our panel āRepresentations for Generalist Robotsā (4-5pm) @corl_conf LEAP workshop! Feat. @chelseabfinn @animesh_garg Vincent Vanhoucke @Marc__Toussaint @sidsrivast and Leslie Kaelbling!
0
0
1
Curious to hear about creating generalist robots from leaders in the field? Donāt miss our panel āRepresentations for Generalist Robotsā (4-5pm) @corl_conf LEAP workshop! Feat. @chelseabfinn @animesh_garg Vincent Vanhoucke @Marc__Toussaint @sidsrivast and Leslie Kaelbling!
0
6
28
RT @corl_conf: Incredible insights from Prof. TomĆ”s Lozano-PĆ©rez of MIT during his keynote on the evolution of robotics! He took us on a joā¦.
0
4
0
RT @AjayMandlekar: Our NVIDIA robotics research team is hiring PhD student interns!. Locations: Bay Area or Seattle. Apply: .
0
21
0
RT @mendonca_rl: Our CoRL 2024 paper shows Reinforcement Learning can allow robots to learn skills via real-world practice, without any demā¦.
0
50
0
Itās been a lot of fun to be part of this work! Failure reasoning is a critical component for robot planning and learning methods, and itās really cool to see how well AHA generalizes to new situations!!.
Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models?. Introducing AHAāa vision-language model for detecting and reasoning over
0
2
6
Weāve decided to extend the submission deadline for this years LEAP workshop - new deadline is October 4!.
0
1
6
RT @shah__naman: Now accepting submissions. šDeadline: Sept 22.šSubmission link available on the website: Submitā¦.
0
4
0
Having been mentored by Tom, I canāt recommend working with him highly enough!! If youāre applying for a PhD this year, youād be quite hard pressed to find a better advisor!.
I am hiring multiple PhD students this year to launch the Princeton Robot Planning and Learning lab:. Thanks for helping me spread the word!.
0
0
10