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…
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… https://t.co/IY36rUvlzs
Even the smartest LLMs can fail at basic multiturn communication
Ask for grocery help → without asking where you live 🤦♀️
Ask to write articles → assumes your preferences 🤷🏻♀️
⭐️CollabLLM (top 1%; oral @icmlconf) transforms LLMs from passive responders into active collaborators.…
How can robots autonomously handle ambiguous situations that require commonsense reasoning?
*VLM-PC* provides adaptive high-level planning, so robots can get unstuck by exploring multiple strategies.
Paper: anniesch.github.io/vlm-pc/
How do we make a scalable RL recipe for robots?
We study batch online RL w/ demos.
Key findings:
- iterative filtered imitation is insufficient
- need diverse policy data, eg using diffusion policy
- policy extraction can hinder data diversity
Paper: pd-perry.github.io/batch-online-r…
How do we make a scalable RL recipe for robots?
We study batch online RL w/ demos.
Key findings:
- iterative filtered imitation is insufficient
- need diverse policy data, eg using diffusion policy
- policy extraction can hinder data diversity
Paper: pd-perry.github.io/batch-online-r…
🧠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
🧠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 https://t.co/pc5R5xgJoN
Was super fun exploring this! Most modern policies don't use history -- Diffusion Policy in particular gets a lot worse. We identify a simple ingredient for history improvement, and use it to improve efficiency and performance of long-context policies.
Was super fun exploring this! Most modern policies don't use history -- Diffusion Policy in particular gets a lot worse. We identify a simple ingredient for history improvement, and use it to improve efficiency and performance of long-context policies.
I’m excited to share a project I’ve been working on for over a year, which I believe will fundamentally change our approach to language models.
We’ve designed a new architecture, which replaces the hidden state of an RNN with a machine learning model. This model compresses…
We've had over a thousand new engineers try Quilter in the last few weeks submitting some really interesting designs. We really want to see some of these come to life, so we're subsidizing board builds!
If you want to build a Quilter design in real life, we'll cover the cost of…
We've had over a thousand new engineers try Quilter in the last few weeks submitting some really interesting designs. We really want to see some of these come to life, so we're subsidizing board builds!
If you want to build a Quilter design in real life, we'll cover the cost of…
Very excited to introduce ROAM, our new work that allows a robot to *adapt on-the-go* as it faces OOD situations during deployment, drawing on pre-trained behaviors.
See as ROAM enables our Go1 to roller skate zero-shot 🤖🐕🛼 (without any lessons!)
🧵(1/9)
We’ve had a flurry of product launches over the past week. Unless you’ve been on X every day, you likely missed a couple.
Here’s a recap of every launch so you can get up to speed👇
98 Followers 380 FollowingResearch Interests - Statistics, Deep Reinforcement Learning.
PhD student @CMU CS.
Prev - Math and CS undergrad at MIT (2021-24) and IISc Bangalore (2020-21).
3K Followers 754 FollowingBuilding graphic design AI models that actually listen to you @world_lica. Fellow @southpkcommons. Ex-@waymo, @snapchat, @microsoft. Lurking on Twitter.
592 Followers 66 FollowingQuliter removes the manual layout bottleneck to make PCB design instant, infinite, and autonomous, so engineers can innovate instead of routing traces.
166K Followers 166 FollowingCo-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log
19K Followers 1K Followingapplied AI @openai. I work with the world's leading startups and developers to bring the benefits of safe AI to every human. views my own 🇮🇳 @dukeu
98 Followers 380 FollowingResearch Interests - Statistics, Deep Reinforcement Learning.
PhD student @CMU CS.
Prev - Math and CS undergrad at MIT (2021-24) and IISc Bangalore (2020-21).
50K Followers 880 FollowingAssistant professor (of mathematics) at the University of Toronto. Algebraic geometry, number theory, forever distracted and confused, etc. He/him.
19K Followers 3K FollowingFrom SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.
6K Followers 2K FollowingCS PhD Student at Stanford Trustworthy AI Research with @sanmikoyejo. Prev interned/worked @ Meta, Google, MIT, Harvard, Uber, UCL, UC Davis
9K Followers 20 FollowingAdvancing humanity's understanding of AI through interpretability research. Building the future of safe and powerful AI systems.
9K Followers 880 FollowingAssistant Professor at University of Washington. I like robots, and reinforcement learning. Previously: post-doc at MIT, PhD at Berkeley
2K Followers 2K FollowingRhodes Scholar researching AI for neuroscience at @UniofOxford, @HarvardDBMI, @WyssInstitute to advance human health. Tweets/RT = my own.