Blog and paper: https://research.nvidia.com/labs/gear/robottt/ Presented to you from NVIDIA GEAR Lab. Please check out Yunfan's technical de…

Blog and paper: https://research.nvidia.com/labs/gear/robottt/ Presented to you from NVIDIA GEAR Lab. Please check out Yunfan's technical deep dive! https://x.com/YunfanJiang/status/2077400992149340552?s=20 We scaled robot policies to 8K timesteps of visuomotor context, orders of magnitude beyond current SoTAs, at constant inference latency. Introducing RoboTTT 🤖 With minutes of experience in context, our robots: 🎥 one-shot imitate human video demos 📈 improve themselves during de…

Related

• Project gallery and whitepaper: https://research.nvidia.com/labs/gear/aspire/ ASPIRE is a great collaboration between NVIDIA GEAR lab, UMich…
• Check out the NVIDIA blog!
• Read the full research post with NVIDIA: http://cursor.com/blog/multi-agent-kernels

Source: Jim Fan (X) | 2026-07-15