Yuzhe Qin

[Yuzhe Qin @qinyuzhe]

Our robots are out here making art now😆 Super cool work @tfortunato.

[Tony Fortunato @tfortunato]

In that spirit, here is my own agent bringing it's self-portrait (& puppy!) into the real world on the @DexmateAI Vega, using a hybrid force-position controller

[Tony Fortunato @tfortunato]

In that spirit, here is my own agent bringing it's self-portrait (& puppy!) into the real world on the @DexmateAI Vega, using a hybrid force-position controller

[Tianyu Li EasyPaperSniper @SniperPaper]

A robot needs to know when a step is done, or it never starts the next one.

In the video, the robot puts the mug upright at 36 s… and keeps going.

Checking "is it done?" sounds easy, but a useful checker has to:
• understand any task and scene, not just follow one hand-written rule
• run often enough to catch the moment, before the robot overshoots
• stay cheap enough to call again and again

So I put today's models to the test: GPT-6 Astra, Gemini, DeepSeek, Qwen, and Jev, a fast text-only decision model. I compared three ways to ask: a VLM judging the camera images directly, a VLM describing the scene and judging its own description, or the same description handed to Jev.

Here's what happened: https://t.co/EMDJAZGvWC

[Dexmate @DexmateAI]

Thank you, IROS 2026.

This week marked a special moment for Dexmate. You witnessed the launch of our new website and new identity, and we got to share this new chapter with the global robotics community in Pittsburgh.

Being a California based company, it’s great to visit Pittsburgh and meet with builders and developer from all around the world. We love meeting with the community and talking about the endless possibilities we can build on Vega.

Thank you to everyone who stopped by and spent time with us. We’re excited for what we’ll build together next.

#IROS2026 #Dexmate #PhysicalAI #Robotics #Humanoid

[Dexmate @DexmateAI]

We're heading to IROS 2026 in Pittsburgh. Booth #200, Sept 28 to 30.
New look. Vega in your hands. The team behind it. And a gift from us.
After party Tuesday with @LightwheelAI and @ADI_News. RSVP before it fills.
https://t.co/Vre4JN8KS4

[Yuzhe Qin @qinyuzhe]

@RewardAI_ Congrats @zipengfu @chenwang_j

[Yuzhe Qin @qinyuzhe]

@yswhynot @physical_int Congrats Yisha!

[Dantong Niu @Dantong_Niu]

Excited to share T-Rex: Tactile-Reactive Dexterous Manipulation 🦖🤖

Touch is fundamental to human dexterity, yet most Vision-Language-Action (VLA) models either ignore tactile feedback or lack the ability to react to high-frequency contact signals.

In this work, we tackle both the data and architectural challenges of tactile-reactive dexterous manipulation.

🦖 A 100-hour tactile-synchronized dexterous manipulation dataset with 7,700+ trajectories, 22 motor primitives, and 200+ everyday objects.

🦖 A tactile-reactive MoT architecture with spatial-temporal tactile encoding and asynchronous high-frequency tactile refinement.

🦖 A scalable training recipe combining 22,889 hours of human egocentric pretraining with tactile-grounded robot mid-training.

Across 12 real-world contact-rich manipulation tasks, T-Rex achieves over 30% higher average success rate than the strongest baseline.

We are fully open-sourcing the dataset, models, teleoperation stack, training code, and inference pipeline.

🌐 Project: https://t.co/AiHKRR8YXU
📄 Paper: https://t.co/mXY2UNLlqc
💻 Code: https://t.co/7skCxUtwKC
🤗 Dataset: https://t.co/uNwW8dcRZL
🧵 Thread ↓

[Dexmate @DexmateAI]

Chicago, we're coming for you⚡

We're heading to Chicago for Automate 2026 (June 22–25), find us at Booth 2484 inside the @NVIDIARobotics Humanoid Pavilion.

Come see how we're bridging the gap between intelligent systems and the physical world.

📍 Booth 2484
🗓️ June 22–25 | Mccormick Place, Chicago IL

#Automate2026 #PhysicalAI #HumanoidRobot #Dexmate #Vega

[Yuzhe Qin @qinyuzhe]

@philippswu @xdofai @YideShentu @itsnemojin 🎉 Congrats Philipp!

[Yuzhe Qin @qinyuzhe]

@litian_liang Congrats @litian_liang , this is amazing teleop tool!

[Dexmate @DexmateAI]

Day 1 at #CVPR is a wrap 🤖
Attendees tried our teleoperation demo firsthand and T-shirts were gone in under an hour 👕
Swing by Booth 612 tomorrow for tote bags, magnets & pins 🙌🏼
And join us at the @NVIDIARobotics Booth at 3:20 PM for a live teleoperation demo session. Come try it yourself.
#Dexmate #Robotics #NVIDIA #CVPR2026 #PhysicalAI #Vega #Technology

[Dexmate @DexmateAI]

🚀 We're excited to announce that Dexmate will be at CVPR 2026 in Denver! 🏔️

Join us at Booth 612 for two live demos:
🎮 Teleoperation: take the controls and drive a dexterous hand in real time.
📸 Vega Snapshot: our robot Vega will snap a Polaroid of you at the booth, yours to keep.
⚡ Both demos run at the edge, powered by @NVIDIARobotics AGX Thor.
🤖 Come interact with Vega, get hands-on with our teleoperation system, and see real-time dexterous manipulation in action.
🗓️ Jun 5–7 📍 Booth 612

#CVPR2026 #Robotics #EdgeAI #DexterousManipulation #PhysicalAI #Dexmate #Vega #NVIDIA #NVIDIATHOR #Denver

[Yuzhe Qin @qinyuzhe]

@zuwang95 Impressive results! Congrats Zu!

[Yuzhe Qin @qinyuzhe]

@Zhenjia_Xu Awesome work Zhenjia!

[Binghao Huang ✈️IROS @binghao_huang]

1/ 🤲 LeRobot has made low-cost robot learning widely accessible — but most policies are still blind to contact.

Today we release LeFlexiTac: a tactile extension for the LeRobot platform using FlexiTac sensors. Make tactile robot learning as easy as possible.

Project page: https://t.co/6PY8oTmAjU
Code/docs: https://t.co/11HW0Zwrtb

[Yuzhe Qin @qinyuzhe]

@xuxin_cheng @DandanShan_ @Meta Big Congrats Xuxin!

[Yuzhe Qin @qinyuzhe]

@xiaolonw @chenbao191541 @Meta Congrats Xiaolong 🎉

[Xiaolong Wang @xiaolonw]

Excited to share that Assured Robot Intelligence (ARI) has joined @Meta to help build the future of humanoid intelligence!

When we started ARI one year ago, our mission was clear: achieve physical AGI. Through deep customer engagements and real-world deployments, it became clear to us that serving the massive opportunity ahead requires training a truly general-purpose physical agent.

We believe this agent will be humanoid — and that scaling will come from learning directly from human experience, not teleoperation alone. Meta’s ecosystem brings together the key components needed to make this vision possible. We will be joining Meta Superintelligence Labs (MSL) to help bring personal superintelligence into the physical world.

We are incredibly grateful to the brilliant minds, robotics researchers, engineers, partners, and supporters who have worked with us on this journey. Thank you to our investors and angels, led by @aixventureshq , for believing in our mission.

This is just the beginning.

[Dexmate @DexmateAI]

MODEX 2026 highlights 🤖
4 days of live Vega demos. Hundreds of hands on the controls.
We're on a mission to lower the barrier to entry for robotics with a unified plug-and-play platform and an open ecosystem that accelerates Physical AI.
📍 Next stop: Automate 2026 — June 22–25, McCormick Place, Chicago. See you there.
#MODEX2026 #Automate2026 #Dexmate #Vega #PhysicalAI #Robotics