Vikash Kumar (@Vikashplus) / X

Vikash Kumar

1,875 posts

Vikash Kumar

@Vikashplus

Building Human-embodied Intelligence. CEO @MyoLabAI | Sr. research scientist @OpenAI @GoogleAI @AIatMeta | @berkeley_ai @UWcse #MuJoCo | Ad. Prof. @CMU_Robotic

NewYorkCity

Joined February 2016

Pinned
Vikash Kumar
@Vikashplus
Jun 23, 2025
📢Life is a sequence of bets – and I’ve picked my next: @MyolabAI It’s incredibly ambitious, comes with high risk, & carries unbounded potential. But it’s a version of the #future I deeply believe in. I believe: ➡️AI will align strongly with humanity - coz it maximizes its own
myolab.ai
@MyolabAI
Jun 23, 2025
All forms of intelligence co-emerged with a body, except AI We're building a #future where AI evolves as your lifelike digital twin to assist your needs across health, sports, daily life, creativity, & beyond... myolab.ai ➡️ Preview your first #HumanEmbodiedAI
00:00
MyoLab
From myolab.ai
30K
Vikash Kumar
@Vikashplus
Aug 8, 2023
#𝗥𝗼𝗯𝗼𝗔𝗴𝗲𝗻𝘁 -- A universal multi-task agent on a data-budget 💪 with 12 non-trivial skills 💪 can generalize them across 38 tasks 💪& 100s of novel scenarios! 🌐robopen.github.io w/ @mangahomanga @jdvakil @m0hitsharma, Abhinav Gupta, @shubhtuls
00:00
86K
Vikash Kumar
@Vikashplus
Sep 13, 2025
Incredible to see how far our ACT(action chuncking transformer) has come. Fun fact- ACT paper was hard to get in. It got conditional accept and we have to do a lot of work to convince the AC of its value.
Ville🤖
@VilleKuosmanen
Sep 13, 2025
RewACT, my reward estimation mod for ACT policies, is now available on PyPi, making it significantly easier to install and use!
00:00
19K
Vikash Kumar
@Vikashplus
Feb 16, 2023
Lack of scale & diversity in robot datasets is demanding a change towards scalable alternatives- LLMs, Sim2Real, etc. GenAug presents a powerful recipe for using text2image generative models to demonstrate widespread generalization of robot behaviors to novel scenarios. 🧵(1/N)
00:00
157K
Vikash Kumar
@Vikashplus
Oct 12, 2023
📢#𝗥𝗼𝗯𝗼𝗛𝗶𝘃𝗲 - a unified robot learning framework ✅Designed for genralizn first robot-learning era ✅Diverse (500 envs, 8 domain) ✅Single flag for Sim<>Real ✅TeleOper Support ✅Multi-(Skill x Task) realworld dataset ✅pip install robohive tinyurl.com/robohive 🧵👇
00:00
51K
Vikash Kumar
@Vikashplus
Sep 17, 2025
Robotics has been plagued by the same problem for decades — trying to find impressive demonstration of hardware+controls capabilities. Robotics is not only a hardware problem — For widespread real world usability we need to robustly solve mundane problem. Problems so ubiquitous
Siyuan Huang
@siyuanhuang95
Sep 17, 2025
Watching the G1 robot doing Webster flip by the side🙀. Such moments make humanoid robot research so much fun 😃😃
00:00
27K
Vikash Kumar
@Vikashplus
Apr 11, 2024
#MuJoCo 3.1.4 drops💧 Lots of new features - - Gravity compensation - Non-linear least squares (ala SysID✅) - MJX features (yup, still no tendons🫤) - many more... mujoco.readthedocs.io/en/latest/chan…
00:00
14K
Vikash Kumar
@Vikashplus
Nov 24, 2023
📢 Announcing a breakthrough in science robotics @SciRobotics - 𝙑𝙞𝙨𝙪𝙖𝙡 𝘿𝙚𝙭𝙩𝙚𝙧𝙞𝙩𝙮 🏳️‍🌈 any object 🌈 any rotation 📉 a low-cost hand (D'Claw) 📷single camera A single policy capable of in-hand reorientation of novel & complex objects (thread👇)
00:00
21K
Vikash Kumar
@Vikashplus
Oct 19, 2023
Just wait until you realize that this is full-blown physics with contacts, not just a visual rendering! 💪#MuJoCo 3.0 is packed with features 👉 XLA: Accelerated physics with JAX 👉 Non-convex collisions 👉Deformable bodies Give it a try - mujoco.org/3
00:00
13K
Vikash Kumar
@Vikashplus
Jun 10, 2024
Human Dexterity is the epitome of motor control. My PhD goal was to study this grand challenge. Amazes me to-date, we found 1st behavioral prior for human dexterity #MyoDex. It's a step change🪜in our understanding, & ability to synthesize, physiological motor control. #proud
Sudeep Dasari
@SudeepDasari
Jul 27, 2023
Excited to present MyoDex at @icmlconf today (poster #200 at 10:30AM) We propose: 🧪 Open-Sourced MyoSuite benchmark w/ 50+ contact-rich manipulation tasks 🧠 The MyoDex prior for quickly learning novel tasks w/ RL 🦾 All validated on a biologically accurate musculoskeletal arm
00:00
22K
Vikash Kumar
@Vikashplus
Oct 3, 2024
What most fails to realize - We can solve problems that are an order more complex than ones found in robotics - Most #RL algorithms don’t direct scale to higher dim search space - contact discontinuities,once considered evil, aren’t daunting anymore 1/N🧵
Alexander Mathis
@TrackingPlumes
Oct 1, 2024
How does the brain control the numerous muscles of the body? Let's say you want to rotate two balls in your hand, how does your brain achieve that? Read our article in @NeuroCellPress to learn more! cell.com/neuron/fulltex…
00:00
17K
Vikash Kumar
@Vikashplus
Nov 4, 2025
I’m worried a bit that @BostonDynamics and @OpenAI story is about to repeat in robotics. The moat of being the first is not that big. Distribution & Adoption will decide the winners.
Nils
@broodsugar
Nov 4, 2025
Replying to @broodsugar
TL;DR: The Chinese are building programmable robots at scale already, and are looking for distributors to help them get the robots ready for specific tasks. They sacrifice some of the upside and share some of the risk. They wish to sell the robot to distributors, today. The
27K
Vikash Kumar
@Vikashplus
Nov 3, 2024
✈️On the way to @corl_conf for my first-ever keynote ℝ𝕠𝕓𝕠𝕥𝕚𝕔𝕤 – 𝕥𝕙𝕖 𝕗𝕦𝕥𝕦𝕣𝕖 𝕚𝕤 𝕒𝕟𝕪𝕥𝕙𝕚𝕟𝕘 𝕓𝕦𝕥 𝕠𝕡𝕥𝕚𝕞𝕒𝕝! a bit excited ✨ & a bit nervous🤪 (+2 more talks. details👇)
17K
Vikash Kumar
@Vikashplus
Oct 18, 2021
It has been a long roller coaster journey that started in 2008 when I was an intern under Emo Todorov. 12 years and now it's in the hands of the open source community. Excited for the next phase ... Big congratulations to team MuJoCo and @DeepMind
Google DeepMind
@GoogleDeepMind
Oct 18, 2021
We’ve acquired the MuJoCo physics simulator (mujoco.org) and are making it free for all, to support research everywhere. MuJoCo is a fast, powerful, easy-to-use, and soon to be open-source simulation tool, designed for robotics research: dpmd.ai/mujoco-blog
GIF