Guanya Shi (@guanyashi) 's Twitter Profile
Guanya Shi

@guanyashi

Assistant Professor @CMU_Robotics @SCSatCMU. Lead the Learning and Control for Agile Robotics Lab @LeCARLab. Ph.D. from @Caltech. Postdoc @uwcse. He/Him/His.

ID: 1071113100739387392

linkhttp://www.gshi.me calendar_today07-12-2018 18:43:58

307 Tweet

5,5K Followers

1,1K Following

Tairan He (@tairanhe99) 's Twitter Profile Photo

Excited to be at #ICRA this week! Working on humanoids, RL, or sim-to-real? Let’s grab coffee—DMs are open. See you there! Presentation for: HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots 📍 Room 307 (Regular Session WeET6: Learning for Legged Locomotion 1) ⏰

Xiaolong Wang (@xiaolonw) 's Twitter Profile Photo

If you are impressed by Tesla Optimus, also check out Roger Qiu 's talk on leveraging human videos for humanoid bimanual manipulation. Paper: Humanoid Policy ~ Human Policy Link: human-as-robot.github.io

Guanya Shi (@guanyashi) 's Twitter Profile Photo

System ID for legged robots is hard: (1) Discontinuous dynamics and (2) many parameters to identify and hard to "excite" them. SPI-Active is a general tool for legged robot system ID. Key ideas: (1) massively parallel sampling-based optimization, (2) structured parameter space,

Guanya Shi (@guanyashi) 's Twitter Profile Photo

Humanoids can run, parkour, dance, and fight nowadays, but can it serve🍺☕️ just like wheeled robots? It could be hard - we found that the default G1 controller yields an average end-effector acceleration ~0.5G (human-level is ~0.05G)! Check-out👇to see how we reduce this

Guanya Shi (@guanyashi) 's Twitter Profile Photo

Great work - Robot/object/contact co-tracking and curriculum via virtual object controllers are really good ideas. We will see similar ideas for humanoid whole-body manipulation and loco-manipulation very soon!

Chonghao Sima (@smch_1127) 's Twitter Profile Photo

🚀 HERE WE GO! Join us at CVPR 2025 for a full-day tutorial: “Robotics 101: An Odyssey from a Vision Perspective” 🗓️ June 12 • 📍 Room 202B, Nashville Meet our incredible lineup of speakers: Dhruv Shah Guanya Shi Davide Scaramuzza Boris Ivanovic Deepak Pathak Angjoo Kanazawa Yilun Du and I

🚀 HERE WE GO! Join us at CVPR 2025 for a full-day tutorial: “Robotics 101: An Odyssey from a Vision Perspective”
🗓️ June 12 • 📍 Room 202B, Nashville

Meet our incredible lineup of speakers: <a href="/shahdhruv_/">Dhruv Shah</a> <a href="/GuanyaShi/">Guanya Shi</a> <a href="/davsca1/">Davide Scaramuzza</a> <a href="/iamborisi/">Boris Ivanovic</a> <a href="/pathak2206/">Deepak Pathak</a> <a href="/akanazawa/">Angjoo Kanazawa</a> <a href="/du_yilun/">Yilun Du</a> and I
Guanya Shi (@guanyashi) 's Twitter Profile Photo

✈️to #CVPR2025 to give three workshop/tutorial talks about learning humanoid whole-body control and loco-manipulation: - Wed 8:30am @ 3D Scene Understanding, 106C - Wed 10am @ Humanoid Agent, 101D - Thu 11am @ Robotics 101 tutorial, 202B Excited to meet old & new friends!

Guanya Shi (@guanyashi) 's Twitter Profile Photo

Very impressive! 2025 will be a year going from single-motion agile WBC policy (e.g., ASAP) to versatile & agile & steerable "Behavioral Foundation Models" for humanoids! We will also likely see research combining such models with VLA-style system2 at the end of 2025!

Danfei Xu (@danfei_xu) 's Twitter Profile Photo

Russ's recent talk at Stanford has to be my favorite in the past couple of years. I have asked everyone in my lab to watch it. youtube.com/watch?v=TN1M6v… IMO our community has accrued a huge amount of "research debt" (analogous to "technical debt") through flashy demos and

Xiaofeng Guo (@xiaofeng2guo) 's Twitter Profile Photo

Arrived in LA for #RSS2025. We'll present the Flying Hand work on Monday afternoon, in the Mobile Manipulation and Locomotion session. Hope to meet old & new friends and chat more on Mobile Manipulation and Dex Manipulation😃

NVIDIA Robotics (@nvidiarobotics) 's Twitter Profile Photo

At #RSS2025, #NVIDIAResearch is advancing agile #humanoidrobot control, sim-to-real transfer, and foundation models for open-world reasoning. Dive into the #robotics research: nvda.ws/4kO5xqu

Guanya Shi (@guanyashi) 's Twitter Profile Photo

Executable action vocabulary naturally exists for manipulation VLA (e.g., end-effector pose). For building humanoid VLA, this paper learns an action vocabulary connecting systems 1&2 that is: 1. Expressive enough and executable for versatile humanoid whole-body control in system

Guanya Shi (@guanyashi) 's Twitter Profile Photo

Recording of my talk "From Sim2Real 1.0 to 4.0 for Humanoid Whole-Body Control and Loco-Manipulation" (at ICRA&CVPR workshops and Caltech): youtu.be/AGNcw4qnimk?si… Slides: drive.google.com/file/d/1h5MxNH…

Recording of my talk "From Sim2Real 1.0 to 4.0 for Humanoid Whole-Body Control and Loco-Manipulation" (at ICRA&amp;CVPR workshops and Caltech): youtu.be/AGNcw4qnimk?si…

Slides: drive.google.com/file/d/1h5MxNH…
Genesis AI (@gs_ai_) 's Twitter Profile Photo

Today, We’re launching Genesis AI — a global physical AI lab and full-stack robotics company — to build generalist robots and unlock unlimited physical labor. We’re backed by $105M in seed funding from Eclipse Ventures, Khosla Ventures, Bpifrance, HSG, and visionaries

Today, We’re launching Genesis AI — a global physical AI lab and full-stack robotics company — to build generalist robots and unlock unlimited physical labor. 

We’re backed by $105M in seed funding from <a href="/EclipseVentures/">Eclipse Ventures</a>, <a href="/khoslaventures/">Khosla Ventures</a>, <a href="/Bpifrance/">Bpifrance</a>, HSG, and visionaries
CMU Robotics Institute (@cmu_robotics) 's Twitter Profile Photo

The team from the RI LeCAR Lab at CMU and the NVIDIA GEAR robotics research lab recently presented ASAP's capabilities at #RSS2025 🤖🚀🦾 The article on this incredible work is out now!: ri.cmu.edu/robots-with-mo…