Antonio Loquercio (@antoniloq) header
Antonio Loquercio (@antoniloq) profile picture

Assistant Professor at #UPenn. Mainly interested in #PhysicalAI

Philadelphia
Joined December 2017
Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)Photo by Antonio Loquercio (@antoniloq)
We found that training (multi-agent) policies to win a race with sparse competitive rewards leads to agile policies with strategic behaviors. These policies outperform the ones trained with behavioral-prescribing dense rewards and transfer better to the real world.
4
3
1
32
5,665
It is really impressive what this model can do (in real time!). Maye the time has arrived for a solid real-time MPC with a video model?
Introducing DreamFAR, a world model trained from scratch using only robot data, without internet pretraining. It supports: 🎮 Real-time teleoperation ⏱️ Minutes of long-horizon rollout 🧩 Generalization across 1,000+ tasks yimingdou.com/DreamFAR 🧵 (1/8)
11
803
Antonio Loquercio retweeted
How should a robot remember what it saw weeks ago: a blue hat with a pink bow, a fire extinguisher, where you left your keys? Today's robot memories caption everything into text first, losing the visual details that make retrieval work. Please meet RAVEN: a long-horizon memory that stores visual embeddings directly — no captioning bottleneck. It answers questions and navigates to goals across days of experience. 🎉 Accepted to the SISREN Workshop at #CoRL2026! 🧵👇 ravenmem.github.io
2
3
1
24
3,212
Can GPT-6 Astra control an FPV drone, predicting control commands directly from images? YES! It was very effective at whatever tasks we threw at it, both in single agent and multi-agent settings. Read more in our blog post: jirl-upenn.github.io/blog/as…
4
1
22
1,343
Antonio Loquercio retweeted
A copilot flies the plane for you. A coach teaches you to fly on your own. What does it take to build an AI coach? We formalize AI coaching as a non-cooperative game where the coach targets the learner's independent competence, then use model-free RL to train coaching policies.
1
4
1
9
1,028
Antonio Loquercio retweeted
[1/5] Fine-grained teleop is slow, error-prone, and frustrating even for experts. We introduce a real2sim2real shared autonomy framework that learns a residual copilot for low-level corrections. It enables: 🎮 fine-grained teleop for novices 🤖 a copilot learned from <5 min of teleop data 📈 higher-quality demonstrations for imitation learning 🔗 residual-copilot.github.io/
4
18
7
118
28,210
Simulation-to-reality transfer for multi-agent policies is still a niche space, but one that (I suspect) has substantial room for discovery and impact.
1
4
343
Led by Vineet Pasumarti and Lorenzo Bianchi Paper: tinylink.net/DJ69A Code: github.com/Jirl-upenn/AgileF…
1
334
Last day of class of my brand-new course Physical Intelligence (lnkd.in/d9BMFG5d) at #UPenn. We concluded with a drone racing competition in the real world! I am really proud of all the students; I have no doubt that they will do great in the future!
7
2
2
94
11,936
Antonio Loquercio retweeted
(1/5) Open Publication and the Prisoners dilemma. The prisoner’s dilemma game can offer us much insight into the publication strategy of leading industrial AI research labs. Suppose there are two labs A and B. If A and B both publish they are both better off than if they both don’t publish as they can build on the results of each other.
13
53
5
362
88,700
Antonio Loquercio retweeted
I am at #NeurIPS2025 Dec 2-7, and presenting our papers including STARFlow. I am also looking for multiple PhD students to join my lab in @CIS_Penn (DDL 12/15), and also research interns at @Apple MLR. Please DM me or come by our posters. Let's chat generative & world models!
STARFlow gets an upgrade—it now works on videos🎥 We present STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows, a invertible, causal video generator built on autoregressive flows! 📄 Paper huggingface.co/papers/2511.2… 💻 Code github.com/apple/ml-starflow (1/10)
6
12
2
85
21,192
Antonio Loquercio retweeted
I will join UChicago CS @UChicagoCS as an Assistant Professor in late 2026, and I’m recruiting PhD students in this cycle (2025 - 2026). My research focuses on AI & Robotics - including dexterous manipulation, humanoids, tactile sensing, learning from human videos, robot systems, and anything needed to make robots truly work and improve everyday life. I also place strong emphasis on open-source. Check my homepage to learn more: haozhi.io/. Please reachout if you are interested! The deadline is Dec 11th. Link: tinyurl.com/uchiapp.
30
98
10
652
108,374
🤖🇮🇹🥳
Congratulations to Antonio Loquercio (@antoniloq) on receiving the 2025 Mario Gerla Young Investigator Award from @issnaf. Recognized for his research on the pivotal role of perception in building effective world models for decision-making, Loquercio enhances the performance of complex robotic systems. He explores how robots can utilize their own sensor data to refine their world models. Congratulations, Antonio! bit.ly/4pbaUSE
1
2
27
3,760
Antonio Loquercio retweeted
My research group at @Princeton has an opening for a postdoc position. Recently, we have been working on foundational research for generalist robots that are safe, trustworthy, and capable: irom-lab.princeton.edu/resea… If you're interested, please email me with the tag [postdoc app] in the subject line.
3
1
35
3,606
Antonio Loquercio retweeted
🤖 Does VLA models really listen to language instructions? Maybe not 👀 🚀 Introducing our RSS paper: CodeDiffuser -- using VLM-generated code to bridge the gap between **high-level language** and **low-level visuomotor policy** 🎮 Try the live demo: robopil.github.io/code-diffu… (1/9)
1
31
5
127
26,831
Antonio Loquercio retweeted
Thanks for coming to our Embodied Intelligence for Autonomous Systems workshop @CVPR We had such a dense & fun program. Videos will be up soon. Kudos to the team: @smch_1127 @AnaMari77147030 @CSakaridis @francislee2020 @PhilionJonah @fbartoc @wongfaikit K. Chitta #cvpr2025
When at @CVPR a major challenge is how to split yourself among super amazing workshops. I'm afraid to announce you that with our workshop on "Embodied Intelligence for Autonomous Systems on the Horizon" we will make this choice even harder: opendrivelab.com/cvpr2025/wo… #cvpr2025
4
17
3,454
I had a completely uneventful drive from an autonomous @wayve_ai car in Nashville. It was amazing.
18
745
We're continuing to push forward the idea of multi-sensory 3D simulators. I believe they will be very useful for AR/VR and (most importantly for me) robotics. If you want to know the key ideas behind it, come to our #CVPR2025 poster today (06/13) at 10:30 (#151).
Ever wondered how a scene sounds👂 when you interact👋 with it? Introducing our #CVPR2025 work "Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes" -- we make 3D scene reconstructions audibly interactive! yimingdou.com/hearing_hands/
13
1,085
Antonio Loquercio retweeted
Our paper is accepted to T-RO @IeeeTro! Code for the learning algorithm is now open-source: t.ly/shgs9 Train your own extreme-adaptive policy today! 🚁🔥
After more than a year of work, we're excited to present a stronger, faster, and more general drone controller! We extend the adaptation range of almost 10X and included the ability to track arbitrary trajectories at up to 3.5 m/s. Paper link: t.ly/TiEU4
1
11
808