Marcel Torné

Giving history to our robot policies is crucial to solve a variety of daily tasks. However, diffusion policies get worse when adding history. 🤖 In our recent work we learn how adding an auxiliary loss that we name Past-Token Prediction (PTP) together with cached embeddings…

Very happy to share that our work on learning long-history policies received the Best Paper Award from the Workshop on Learned Robot Representations @RoboticsSciSys ! 🤖🥳 Check out our paper if you haven't already! long-context-dp.github.io Thank you to all the organizers and…

I farem estada a Standford Califòrnia amb el @marceltornev

🧠Memory is crucial for robots — to handle occlusions, track progress, stay coherent, etc. Yet, most VLA truncate context. 🤔Why is long-context hard for robot policies? And how can we fix it? 📄Our new paper: Learning Long-Context Diffusion Policies via Past-Token Prediction

This is very very cool!! You should try it out! Congrats to @sequoia on making the great decision to back @itsalfredw and @florian_jue !

AI writes your code. Now it talks to your users. We raised $27M from @Sequoia to build @ListenLabs. Listen runs thousands of interviews to uncover what users want, why they churn, and what makes them convert. See how @Microsoft and @canva use it:

Not all human-collected demos are created equal: ✔️ All are successful ❌ But some strategies are unreliable or brittle This can hurt final performance. Demo-SCORE self-curates reliable training data using online experience. Paper and videos: anniesch.github.io/demo-score/

Robots can do flips and play chess, but they still can’t grab a snack or clean your table. Teleoperation is the key to unlocking real dexterity. It’s not a compromise—it’s a proven, powerful approach that combines human intuition with robotic precision. We’re not just using…

Overcoming the lack of reliability of Behavior cloning (BC) with reactive reinforcement learning. Action-chunking is a two-edged sword- it's critical for BC to work, but it also limits how adaptive the robot is to disturbances and corner cases. Learn more:…

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been…