Simar Kareer (@simar_kareer) 's Twitter Profile
Simar Kareer

@simar_kareer

Research Intern at π | PhD at GT

ID: 1082744307059175426

linkhttp://www.simarkareer.com calendar_today08-01-2019 21:02:13

46 Tweet

330 Followers

94 Following

Simar Kareer (@simar_kareer) 's Twitter Profile Photo

If you’re looking to study domain adaptation on videos, definitely try out our paper / code with reproducibility certification! github.com/SimarKareer/Un…

Danfei Xu (@danfei_xu) 's Twitter Profile Photo

🤖 Inspiring the Next Generation of Roboticists! 🎓 Our lab had an incredible opportunity to demo our robot learning systems to local K-12 students for the National Robotics Week program Robotics@GT . A big shout-out to Vaibhav Saxena @ ICLR 2025 Simar Kareer Pranay Mathur for hosting

🤖 Inspiring the Next Generation of Roboticists! 🎓

Our lab had an incredible opportunity to demo our robot learning systems to local K-12 students for the National Robotics Week program <a href="/GTrobotics/">Robotics@GT</a> . A big shout-out to <a href="/saxenavaibhav11/">Vaibhav Saxena @ ICLR 2025</a> <a href="/simar_kareer/">Simar Kareer</a> <a href="/pranay_mathur17/">Pranay Mathur</a> for hosting
Ignat Georgiev (@imgeorgiev) 's Twitter Profile Photo

We have a new ICML paper! Adaptive Horizon Actor Critic (AHAC). Joint work with Krishnan Srinivasan Jie Xu Eric Heiden Animesh Garg AHAC is a first-order model-based RL algorithm that learns high-dimensional tasks in minutes and outperforms PPO by 40%. 🧵(1/4)

Fiona Ryan (@fionakryan) 's Twitter Profile Photo

Introducing Gaze-LLE, a new model for gaze target estimation built on top of a frozen visual foundation model! Gaze-LLE achieves SOTA results on multiple benchmarks while learning minimal parameters, and shows strong generalization paper: arxiv.org/abs/2412.09586

Lucy Shi (@lucy_x_shi) 's Twitter Profile Photo

Introducing Hi Robot – Hierarchical Interactive Robot Our first step at Physical Intelligence towards teaching robots to listen and think harder. A 🧵 on how we make robots more steerable 👇

Physical Intelligence (@physical_int) 's Twitter Profile Photo

We are excited to share new experiments with AgiBot AgiBot on multi-task, multi-embodiment VLAs! With one model that can perform many tasks with both two-finger grippers and multi-fingered hands, we take another step toward one model for all robots and tasks.

Simar Kareer (@simar_kareer) 's Twitter Profile Photo

Mobile manipulation is hard, and generalizing to new environments is even harder. We take a stab at both in our latest release, where our robots clean Airbnbs they've never been to!

Lerrel Pinto (@lerrelpinto) 's Twitter Profile Photo

Imagine robots learning new skills—without any robot data. Today, we're excited to release EgoZero: our first steps in training robot policies that operate in unseen environments, solely from data collected through humans wearing Aria smart glasses. 🧵👇