Sciencer | PhD Princeton. Building skynet one robot at a time :)
Joined August 2017
- Tweets29
- Following1.8K
- Followers102
- Likes1.6K
Pinned Tweet
Excited to show the results of our latest work at #CoRL2025!
Can robots learn to jump, crawl, and climb—without reward engineering, curriculum learning, or reference data?
In our #CoRL2025 paper SDAX, Skill Discovery as eXploration, we show how unsupervised RL can learn these challenging motor skills without human priors —and transfer them to real robots.
📷 Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion
Seungeun Rho* @ross_rho , Kartik Garg* @_pacificax, Morgan Byrd, Sehoon Ha @sehoonha
seungeunrho.github.io/projec…
Kartik Garg retweeted
🚨 Stop feeding your world model the same boring demos. Switch to free-range play data! 🚨
Our CoRL 2026 paper finds we can optimize autonomous data collection to focus on missing action consequences, achieving up to 85x the data scaling efficiency of expert data collection!🧵
Kartik Garg retweeted
Happy to see interest for our paper! Those at #ECCV2024 @eccvconf, revisit #RevisitAnything at board no 244 tomorrow (3rd Oct) from 10:30 am - 12:30 pm. ✨
Looking for PhD opportunities, request hiring professors to drop by! 🙏
On left as soon as you climb down stairs. ⬅️
Places are composed of things. Recognizing & retrieving these things instead of the whole image enables
🧭viewpoint invariance
🖼️semantic interpretability
🔮open-set recognition
🧵on our #ECCV2024 paper:
Revisit Anything: Visual Place Recognition via Image Segment Retrieval
👇
Kartik Garg retweeted
Here’s our new #VPR take on the good old ‘revisiting problem’ in #SLAM / #localization
#ECCV2024 @eccvconf
Incredible effort by @shubodhs_ai and @_pacificax
Catch @shubodhs_ai in person at the venue
ILR Workshop: 30 Sep, 10-11am CEST
Main Conf: 3 Oct, 10:30am-12:30pm CEST
Places are composed of things. Recognizing & retrieving these things instead of the whole image enables
🧭viewpoint invariance
🖼️semantic interpretability
🔮open-set recognition
🧵on our #ECCV2024 paper:
Revisit Anything: Visual Place Recognition via Image Segment Retrieval
👇
Happy to share our new #VPR work that has been accepted to #ECCV2024 @eccvconf!
Thanks to my amazing collaborators @shubodhs_ai @shishirny Madhav Krishna and @sourav_garg_
(P.S. Also my first publication in a top tier conference 😊)
Places are composed of things. Recognizing & retrieving these things instead of the whole image enables
🧭viewpoint invariance
🖼️semantic interpretability
🔮open-set recognition
🧵on our #ECCV2024 paper:
Revisit Anything: Visual Place Recognition via Image Segment Retrieval
👇
Kartik Garg retweeted
Revisit Anything: Visual Place Recognition via Image Segment Retrieval
Kartik Garg, Sai Shubodh Puligilla, Shishir Kolathaya, Madhava Krishna, @sourav_garg_
tl;dr: encoding and searching for image segments instead of the whole images
arxiv.org/pdf/2409.18049
