Quan Vuong
@QuanVng
Followers
3K
Following
6K
Media
19
Statuses
462
robotics research and co-founder at @Physical_int, ex-@GoogleDeepMind Perpetually trying to find a quiet place to read.
Joined January 2015
And we're hiring! Apply on our website or DM me with questions
We got a robot to clean up homes that were never seen in its training data! Our new model, π-0.5, aims to tackle open-world generalization. We took our robot into homes that were not in the training data and asked it to clean kitchens and bedrooms. More below⤵️
4
7
183
🌠
Our model can now learn from its own experience with RL! Our new π*0.6 model can more than double throughput over a base model trained without RL, and can perform real-world tasks: making espresso drinks, folding diverse laundry, and assembling boxes. More in the thread below.
1
3
43
we're hiring a handful of extremely high priority roles at @physical_int -- our first business hires (focused on scaling our research operations and data), a floor/shift manager for our data collection sites, engineers who are looking to transition into ops, and a weirder/more
pi.website
Physical Intelligence is bringing general-purpose AI into the physical world.
22
32
627
Telexistence 🤝 PI
We are pleased to announce a partnership with Physical Intelligence ! Here we started working together on automating drink-restocking operations in retail stores, especially the anomaly cases where manual teleoperation was required to recover from, by combining our robots and
1
3
12
At @physical_int, we have open roles robotics research scientist and research engineer. If you love robots, hands-on experimental robotics work, and getting amazing, dexterous skills to work, get in touch! See https://t.co/I9TEDtQ9VP
6
31
381
We asked π₀.₅ — trained mostly on data from other robots and the web — to “load the dishes” and “make the bed” in homes it had never seen. It parsed the instructions, planned, and executed end‑to‑end. This isn’t just a research milestone; it’s a real step toward
2
22
84
Super proud about this release. We placed our robots in a never before seen environment, and asked them to do a full kitchen / bedroom cleanup autonomously! By no means perfect, but its super exciting to see this really working (can you tell from my reaction in the video 😂)
We got a robot to clean up homes that were never seen in its training data! Our new model, π-0.5, aims to tackle open-world generalization. We took our robot into homes that were not in the training data and asked it to clean kitchens and bedrooms. More below⤵️
7
26
148
Flying to Singapore 🇸🇬 for @iclr_conf this week! Looking forward to catching up with friends and discuss multimodal modeling or our new π-0.5 https://t.co/M76KnVM6Yt (and other Visual language action models).
physicalintelligence.company
Our latest generalist policy, π0.5, extends π0 and enables open-world generalization. Our new model can control a mobile manipulator to clean up an entirely new kitchen or bedroom.
3
11
98
We got a robot to clean up homes that were never seen in its training data! Our new model, π-0.5, aims to tackle open-world generalization. We took our robot into homes that were not in the training data and asked it to clean kitchens and bedrooms. More below⤵️
53
258
2K
Attending #ICLR2025 next week! I will be presenting Diffusion Policy Policy Optimization (DPPO) at the Friday morning poster session with @larsankile
https://t.co/uOkkcnVFCf I also joined @physical_int lately. Love to chat about what we've been up to at Pi!
0
8
146
Excited to announce the 1st Workshop on Robot Hardware-Aware Intelligence @ #RSS2025 in LA! We’re bringing together interdisciplinary researchers exploring how to unify hardware design and intelligent algorithms in robotics! Full info: https://t.co/1ZbYZRm0aM
@RoboticsSciSys
5
17
66
We are excited to share new experiments with AgiBot @AgiBot_zhiyuan on multi-task, multi-embodiment VLAs! With one model that can perform many tasks with both two-finger grippers and multi-fingered hands, we take another step toward one model for all robots and tasks.
10
63
392
Happy Valentines Day! 🌹 Enjoy a special Valentine's day themed policy (sound on!) from the AquaBot team 👬❤️🦾 Visit https://t.co/nt7mxVCgpb to learn more about our recent ICRA publication!
5
6
61
And we're also hiring! apply directly on our website or dm me with questions!
Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and pre-trained checkpoints in our new openpi repository! We tested the model on a few public robots, and we include code for you to fine-tune it yourself.
4
4
88
Celebrate the inaugural "Intangible Cultural Heritage Spring Festival" with Astribot S1, and immerse yourself in world's cultural treasures 🤖🧧🎆 #AIRobot #EmbodiedAI #Humanoid #SpringFestival #CulturalPreservation #AI #Astribot
0
6
16
I'll be speaking at Founders You Should Know in SF on Feb 5th about Physical Intelligence (π.com) -- our progress and why you should join. Plus it's a great place to meet founders of some of the best SF startups! Apply to join at https://t.co/QaPKm91Awj
@foundersysk @nifferkin
foundersysk.com
Information
2
3
39
Excited to release FAST, our new robot action tokenizer! 🤖 Some highlights: - Simple autoregressive VLAs match diffusion VLA performance - Trains up to 5x faster - Works on all robot datasets we tested - First VLAs that work out-of-the-box in new environments! 🧵/
20
96
527
How can we train high-frequency generalist robot policies with next-token prediction? In new work with @KarlPertsch/@physical_int we achieve SoTA generalist VLAs with way less training! Highlight: we train a VLA on DROID that can do zero-shot language tasks in the wild!
9
30
162
i'm hiring an engineer that loves operations. we will work very closely. need to be comfortable building usable frontends, iterating quickly with users, love creating leverage and efficiency, very creative and high agency. DMs open. will pay generous referral bonus.
11
15
226
I'm hiring exceptional researchers, engineers (both research and full-stack) at @physical_int. Please apply on our website or DM me with questions. Referrals very appreciated!
10
25
232