In January, I started "building something new" with an incredible team. Today I finally get to share some first details about what we've been building. We've called it Walden Robotics (https://t.co/LVSojsX8aJ).
I thought long and hard about my own reasons for starting this company. It's not only about the robots. It's also about people. I've tried to capture those thoughts in my first Walden blog post: https://t.co/Lmo1CU8tLF
It's been an incredible ride so far. Within just a few months of forming the company, we were already operating a general-purpose robot with an end-to-end policy in production in one of the most important factories in North America. It's amazing at how much I've already learned from that experience. There is a lot of work to do, but the mission has never been so clear.
Please help me welcome Walden Robotics into the world. And stay tuned for more updates!
https://t.co/vaVRt0JFY1
Announcing OpenThinker3-7B, the new SOTA open-data 7B reasoning model: improving over DeepSeek-R1-Distill-Qwen-7B by 33% on average over code, science, and math evals.
We also release our dataset, OpenThoughts3-1.2M, which is the best open reasoning dataset across all data scales. Full details are in our ✨new paper✨ - below we share the highlights:
BTW, it also works on non-Qwen models😉 (1/N)
Meet ProVox: a proactive robot teammate that gets you 🤖❤️🔥
ProVox models your goals and expectations before a task starts — enabling personalized, proactive help for smoother, more natural collaboration. All powered by LLM commonsense.
Recently accepted at @ieeeras R-AL!
🧵1/7
Image/video models can transfer knowledge from Internet data to robot agents by generating goal images. But what happens when images have harmful visual artifacts? We present GHIL-Glue, a method to align image/video models and low-level policies.
https://t.co/PLnT6ENezk
Learned visuomotor robot policies are sensitive to observation viewpoint shifts, which happen all the time. Can visual priors from large-scale data help? Introducing VISTA: using zero-shot novel view synthesis models for view-robust policy learning! #CoRL2024
🧵👇
After two years, it is my pleasure to introduce “DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset”
DROID is the most diverse robotic interaction dataset ever released, including 385 hours of data collected across 564 diverse scenes in real-world households and offices
Access to *diverse* training data is a major bottleneck in robot learning. We're releasing DROID, a large-scale in-the-wild manipulation dataset. 76k trajectories, 500+ scenes, multi-view stereo, language annotations etc
Check it out & download today!
💻: https://t.co/JsbBZIxzZA
ICRA 2022 AV workshop videos now online:
🚗 keynotes: https://t.co/Bsnqx59LYe
🚗 authors: https://t.co/nPB5oLjSMJ
🚗 all: https://t.co/xxFvUYqi23
Thanks to lead organizer @corina_gurau, virtual org @wulfebw@hu_anth@pondruska@blazejosinski, PC members + authors + attendees!
How should models be trained? We show weighting model errors by their effect on downstream control improves accuracy where it matters most (gif) + improves end performance
https://t.co/qxv3oXmEux
https://t.co/VDAUTsy7PX
w @wulfebw@MercatJean@logan_m_ellis@svlevine@adnothing