Kevin Zakka (@kevin_zakka) 's Twitter Profile
Kevin Zakka

@kevin_zakka

phding @Berkeley_AI

ID: 4764525630

linkhttps://kzakka.com/ calendar_today15-01-2016 21:03:50

2,2K Tweet

14,14K Followers

948 Following

Laura Smith (@smithlaura1028) 's Twitter Profile Photo

My goal throughout my PhD has been to take robots out of the lab and into the real world. It was so special to be a part of this effort and see this dream become reality! Excited to keep pushing model capabilities—and, of course, keep playing with robots 🤖

Google DeepMind (@googledeepmind) 's Twitter Profile Photo

We built an AI model to simulate how a fruit fly walks, flies and behaves – in partnership with HHMI | Janelia. 🪰 Our computerized insect replicates realistic motion, and can even use its eyes to control its actions. Here’s how we developed it – and what it means for science. 🧵

Seohong Park (@seohong_park) 's Twitter Profile Photo

What is the RL equivalent of "next-token prediction"? Our answer is offline *goal-conditioned RL*. We also made a clean, easy-to-use benchmark. Come see our poster at #387 tomorrow morning! (4/26 Sat, 10am-12:30pm) Project page: seohong.me/projects/ogben…

What is the RL equivalent of "next-token prediction"?

Our answer is offline *goal-conditioned RL*. We also made a clean, easy-to-use benchmark.

Come see our poster at #387 tomorrow morning! (4/26 Sat, 10am-12:30pm)

Project page: seohong.me/projects/ogben…
-T.K.- (@t_k_233) 's Twitter Profile Photo

Humanoid robots should not be black boxes 🔒 or budget-busters 💸! Meet Berkeley Humanoid Lite! ▹ 100% open source & under $5k ▹ Prints on entry-level 3D printers—break it? fix it! ▹ Modular cycloidal-gear actuators—hack & customize towards your own need ▹ Off-the-shelf

Zhongyu Li (@zhongyuli4) 's Twitter Profile Photo

Command humanoids *directly* with natural language? Introducing LangWBC, a generative, end-to-end policy that turns natural language into real-world whole-body humanoid control! 💬→🦿Smooth, robust, surprisingly intuitive! See more 👉 LangWBC.github.io #RSS2025

Yanjie Ze (@zeyanjie) 's Twitter Profile Photo

🤖Introducing TWIST: Teleoperated Whole-Body Imitation System. We develop a humanoid teleoperation system to enable coordinated, versatile, whole-body movements, using a single neural network. This is our first step toward general-purpose robots. 🌐humanoid-teleop.github.io

Chung Min Kim (@chungminkim) 's Twitter Profile Photo

Excited to introduce PyRoki ("Python Robot Kinematics"): easier IK, trajectory optimization, motion retargeting... with an open-source toolkit on both CPU and GPU

Catherine Glossop (@catglossop) 's Twitter Profile Photo

Leveraging large-scale data sources can enable extremely general and robust policies. See our recent work MBRA! model-base-reannotation.github.io Led by noriaki_hirose Dhruv Shah Kyle Stachowicz Lydia Ignatova, Sergey Levine and thanks FrodoBots for making large-scale data for nav possible!

K-Scale Labs (@kscalelabs) 's Twitter Profile Photo

In the last month, we’ve been building an open-source framework for robot learning and sim-to-real transfer, made for RL whole-body control from simple walking to complex human imitation Check out the details on HN: news.ycombinator.com/item?id=440221… Get started in 5 minutes ⬇️

Younggyo Seo (@younggyoseo) 's Twitter Profile Photo

Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-source code to run your own humanoid RL experiments in no time! Thread below 🧵

Seohong Park (@seohong_park) 's Twitter Profile Photo

Is RL really scalable like other objectives? We found that just scaling up data and compute is *not* enough to enable RL to solve complex tasks. The culprit is the horizon. Paper: arxiv.org/abs/2506.04168 Thread ↓

NVIDIA Robotics (@nvidiarobotics) 's Twitter Profile Photo

Join experts Yuval Tassa from Google DeepMind and Miles Macklin from NVIDIA at #GTCParis to learn about Newton, an open-source, extensible physics engine for robotics simulation, co-developed by Disney Research, Google DeepMind and NVIDIA. Gain insights into breakthroughs in

Priya Sundaresan (@priyasun_) 's Twitter Profile Photo

How can we move beyond static-arm lab setups and learn robot policies in our messy homes? We introduce HoMeR, an imitation learning agent for in-the-wild mobile manipulation. 🧵1/8

Priya Sundaresan (@priyasun_) 's Twitter Profile Photo

Specifically, HoMeR builds on our prior work SPHINX: x.com/priyasun_/stat… extending it to Jimmy Wu‘s Tidybot++: x.com/jimmyyhwu/stat… with a whole-body controller based on Kevin Zakka‘s mink! x.com/kevin_zakka/st… 🧵4/8

Binit Shah (@binitshah_) 's Twitter Profile Photo

Excited to get this release out there! It's been cool seeing sw made for the real robot function identically in sim. Also really glad to be building on MuJoCo; their codebase & docs are incredible

Carlo Sferrazza (@carlo_sferrazza) 's Twitter Profile Photo

Looking forward to giving a talk at the Real2Sim workshop at #CVPR2025 today at 3:50pm CDT. I will be speaking about sim-to-real for robot learning -- and MuJoCo Playground! #CVPR2025