Here is what it feels to be an autoregressive LLM. I show you a question, and ask you to write an answer. You write the first word, and then I zap you with a taser so that you forget what you just did. 1/2

📣 Call for Submissions - X-Sense Workshop #ICCV2025! Let's accelerate Ego-Exo Sensing for cleaner, safer, and more efficient mobility experience! 🚀✨ 📅 Deadline: August 31, 2025 09:59 AM GMT 📝 Submission Portal: lnkd.in/gyeRFYQv 🌐 More info: lnkd.in/gZkdWi8m

And we won the #RSS 2025 Best Paper Award! Congrats Rajat Kumar Jenamani and the entire EmPRISE Lab team Cornell Bowers Computing and Information Science 🎉🎉

DSO is accepted at #ICCV2025! A feed-forward 3D generator that directly outputs physically stable objects, even for in the real world Huge thanks to the amazing team Visual Geometry Group (VGG): RuiningLi, Christian Rupprecht, and Andrea Vedaldi!

Teleoperation is slow, expensive, and difficult to scale. So how can we train our robots instead? Introducing X-Sim: a real-to-sim-to-real framework that trains image-based policies 1) learned entirely in simulation 2) using rewards from human videos. portal-cornell.github.io/X-Sim

Huge thanks to my co-lead Prithwish Dan, collaborators Angela Chao, Edward Duan & Maximus Pace, and co-advisors Wei-Chiu Ma Sanjiban Choudhury! Thrilled that our X-Sim paper received Best Paper (Runner-Up) at the EgoAct Workshop Robotics: Science and Systems — winning a cool pair of Meta Ray-Bans! 😎

We released COLMAP v3.12, which adds long-awaited end-to-end support for multi-camera rigs and 360° panoramas 👀 COLMAP just got better at handling your robotics, AR/VR, or 360 data - try it and let us know! github.com/colmap/colmap/… Kudos to Johannes & team for this great work 🚀

🎉 Meshy is now the first official AI 3D sponsor of Blender 🔶 ! 🤝 You can import 3D models & animations straight from Meshy to Blender with Meshy-Blender Plugin. 🚀 Fast generation + pro-level editing = creative superpowers. Let's shape the future of 3D, together! #Blender3d

Kosta Derpanis your view is much better, but this slide 💯 !

Introducing Muscle v0 -- infinite degrees of freedom, from Daxo Robotics. A different mountain to climb - with a far more beautiful peak. We built this from the ground up: - Ultra-dexterous - Built for machine learning - Durable and robust More below (1/n)

🚀 Check out Ke Fan(FFFFFFF)’s #ICCV25 paper: "GO TO ZERO" – the first systematic exploration of zero-shot text-to-motion generation! Huge congratulations to Kefan and the whole team! Highlights: ✅ 2M+ 3D motion clips ✅ A new benchmark with 126 real-world prompts ✅ A

Can we build an operating system entirely powered by neural networks? Introducing NeuralOS: towards a generative OS that directly predicts screen images from user inputs. Try it live: neural-os.com Paper: huggingface.co/papers/2507.08… Inspired by Andrej Karpathy's vision. 1/5

Large foundation models trained on massive datasets have revolutionized #AI. Supported by a Google Research Ph.D. Fellowship, University of Washington #UWAllen’s Cheng-Yu Hsieh aims to make the process more efficient and affordable to democratize AI development. #UWdiscovers news.cs.washington.edu/2025/07/09/all…

One amusing takeaway from doing RL in these massively parallelized sim environments is that reward engineering matters more so than ever. A small detail in reward function could make a huge difference: with 10k+ parallel threads to explore in, the policy Will exploit any caveat