Dexmate

One platform. Everything Physical AI Needs.

[Dexmate @DexmateAI]

What a great two days at Encord's Long Horizon Summit 2026! 🤖

Insightful talks, great conversations with Physical AI builders, and lots of excitement around Vega’s live demos!

Thanks to @encord_team for bringing the Physical community together. Looking forward to what’s next!

#PhysicalAI #Robotics #Dexmate #Vega #Longhorizon

[Dexmate @DexmateAI]

@anand_bhattad Happy to support your research, Anand! Excited to see what your team is building, and looking forward to more collaborations! :)

[Dexmate @DexmateAI]

Howdy, Austin! 🤠 Dexmate is heading to CORL 2026 @corl_conf!

🤖 Catch Vega in action at Booth #1104, Nov 9–12.

🎉 We’re also hosting our own afterparty on Nov 10! Come hang out with the Physical AI community.

RSVP: https://t.co/chDyVtANnI

See y’all in Austin!

[Dexmate @DexmateAI]

Amazing work by the Johns Hopkins team on tactile sensing and compliant control! Proud to support researchers pushing the boundaries of what’s possible with Physical AI through our Research Grant Program.

[Krishna Murthy @_krishna_murthy]

We strapped an OpenTac skin on the forearm of a @DexmateAI Vega-1 robot. We can sense external contacts and nudge the robot around by implementing a compliant controller that monitors pushes and complies with the direction of each push.

[Eventual @eventualai]

@DexmateAI The full 7-minute interview with @EverettKleven

[Dexmate @DexmateAI]

@eventualai @everettkleven Thanks for the awesome deep dive into our robot Vega! Great to connect with the Physical AI community at Long Horizon Summit and share what builders can create with Vega. Excited to see what’s next!😊

[Dexmate @DexmateAI]

🤖 What should a robot remember? Text? Image? Scene Graph?

Memory is essential for Physical AI. The problem is not as easy as it first look. It a balance between task success, storage as well as cost of saving and reuse. Different represent and lead to different results.

Our latest research, developed in collaboration with researchers at Carnegie Mellon University, including @wang_junxiang_ and @SniperPaper, introduces MeMoREval, a benchmark evaluating robot memory representation across 53 tasks in four environments.

The findings: Storing camera frames achieved 70% task success, compared to 56–60% with text descriptions. Combining visual memory with scene graphs further improved performance to 75%, highlighting the importance of preserving both visual and spatial information.

Beyond memory representation lies a broader challenge: How should robots decide what information is worth retaining as their experiences grow?

💬 For the Physical AI community: How should we structure a general memory system for robots, what should we prioritize? past experiences, future task relevance, or a combination of both?

We’d love to hear how you’re approaching this challenge.

🔗 Read the full blog: https://t.co/ESiE2kENnj
#PhysicalAI #Robotics #RobotLearning #Dexmate #Blog #Vega #CMU

[Lukas Ziegler @lukas_m_ziegler]

There are more companies selling robot intelligence right now than companies selling robots. 

That showed up this year as a pattern I kept noticing. 

In this case all these research groups with published on the same robot from @DexmateAI.

DeepMind’s Gemini Robotics 2 launch video. Amazon FAR’s real-world RL on a dexterous humanoid. DUET, the dual-robot manipulation framework from USC, Stanford and TRI.

A 100-hour tactile dataset from Berkeley, NVIDIA and Stanford. World Labs’ Atlas launch. And a Mayo Clinic residency track, which is not a robotics lab at all.

The platform in all of them is Vega, from Dexmate.

Models, VLAs, data engines, simulators, teleop stacks: that side of the market is crowded.

The side that will sell a lab a capable bimanual mobile robot, this quarter, at a published price, is thin.

So a team with a policy to validate either waits on a partnership or spends a year building a platform that was never the point of the paper.

Dexmate sells the platform. Look at what the spec sheet commits to, and what it refuses:

→ Vega 1 Pro, $75,000 at this year’s pricing, roughly four weeks from order
→ 24 DoF, torso from floor to 2.2 m, 5 kg per arm, omni base, ~20 h per charge
→ Jetson AGX Thor, stereo head, two LiDAR, four base cameras
→ Python, C++ and Rust APIs in the box
→ SimReady URDF and USD models matching the shipped robot

Not the model company, not the data company, not the simulation company. The thing they run on.

Congrats @taochenshh, @qinyuzhe and the team! :)

~~ 

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[Dexmate @DexmateAI]

@lukas_m_ziegler Thanks for the great feature, Lukas! 🙌 That’s exactly our mission: making Physical AI more accessible by removing hardware barriers. Excited to see what’s next!

[Junxiang Wang @wang_junxiang_]

A robot constantly receives multimodal information—textual states, camera images, 3D maps—but what is the “best” modality to save in memory? Is text enough?

Introducing MeMoREval, my internship project at @DexmateAI, where we evaluate memory modality for embodied agents.
🧵

[Dexmate @DexmateAI]

@wang_junxiang_ Exciting to see this work come out of your internship at Dexmate! Congrats on the paper, Jim! It was a pleasure having you on the team, and we’re proud to see your research contributing to the Physical AI community!

[Dexmate @DexmateAI]

Congratulations to @RoboStrategy on ringing the Nasdaq Closing Bell!

We were excited to bring Vega to New York City and celebrate this milestone alongside the RoboStrategy team and fellow robotics founders.

Advancing Physical AI takes engineers, founders, and investors working together. RoboStrategy is helping connect robotics innovation with public markets, opening new opportunities for the broader ecosystem.

Here’s to bringing more people into the future of Physical AI.

Learn more about RoboStrategy: https://t.co/u67u7BFeri

#RoboStrategy #Dexmate #PhysicalAI #Robotics #Nasdaq #Vega

[Dexmate @DexmateAI]

We’re heading to @encord_team 's Long Horizon Summit! 🤖

Catch Vega in action and connect with the Dexmate team at the Physical AI Summit.

📅 Oct 20–21
📍 Fort Mason, San Francisco
🤖 Booth A3

See you there!

🔗 https://t.co/pAAHKGLlXv

#PhysicalAI #Robotics #Dexmate #Vega #Longhorizon #Encord

[Andrew Kang @Rewkang]

We’re ringing the Nasdaq closing bell with a bunch of @RoboStrategy portfolio robots next week

Before that we’ll be hosting a Robotics Forum with the founders and senior leaders from @Apptronik, @standardbots, @DynaRobotics, @DexmateAI, @mavenrobotics, @PathRobotics, @noxmetals and more

Who are the best large public equity managers interested in robotics? We have a few spots reserved for them.

https://t.co/8bUbNpGEUC

[Dexmate @DexmateAI]

@RuixuanLiu_ Proud to have supported RoCo Challenge at IROS 2026! Incredible to see teams from around the world pushing the boundaries of robotic manipulation. Huge thanks to the organizers and everyone who made this possible. Excited to see what's next!

[Ruixuan Liu @RuixuanLiu_]

Here's the recap of the 2nd RoCo Challenge: 55 teams from 8+ countries, 7 onsite finalists in Pittsburgh, two tracks (Industrial Board Assembly + Brick Assembly), two embodiments (Grippers + Dexterous Hands), and a $20K prize pool.

Proud of every team that made it to the finals, and grateful to the volunteers, sponsors @SharpaRobotics, @DexmateAI, @AvantRobotics, @roboforce_ai, @TARSRobotics, @eastworlds_io, and co-organizers who made it happen.

Check out earlier announcement of the competition result: https://t.co/SNtyZrC4ny.

See you at RoCo 2027 → https://t.co/ak9DRISDSM

#IROS2026 #Robotics #PhysicalAI #RoCoChallenge #Manipulation

[Dexmate @DexmateAI]

We’re teaming up with @CoreWeave for the Physical AI Happy Hour during SF Tech Week tomorrow night.

Come meet the CoreWeave Physical AI team, connect with the robotics community, see what we’re building at Dexmate, and get a custom cap made live by our robot.

📍 Mission District, San Francisco
🔗 RSVP: https://t.co/kwn8pQBl8A

See you there!

#Dexmate #CoreWeave #PhysicalAI #Robotics #SFTechWeek

[Dexmate @DexmateAI]

@tfortunato This is amazing, love seeing Vega bring this to life!

[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

[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