Aniketh Cheluva

The future of content creation is just a few words away. Join the waitlist irisvideo.app

Our latest project ‼️

@physical_int pi0.5 + 120 robot demos keeps going on and on and on and on 🤩

@ryan_punamiya @physical_int We are locked in

@AbhinavMar9985 @GeorgiaTech looks sick

🚀 Something new is in motion. We’re building a platform that makes robotics as simple as drag-and-drop. From kitchens to warehouses, we’re helping businesses integrate automation without the complexity. Website coming soon 👀 #RaaS #Automation @startupxchange

Robots struggle to learn new skills from human videos. Why? We found that naive co-training produces disjoint distributions. Our EgoBridge (NeurIPS’25) extends Optimal Transport to align human-robot latents, improving success by 44% and generalization to human-only tasks!🧵

@DaffaReinaro @startupxchange Cant wait to see it

Building this for the next 5 weeks @startupxchange

Can we scale up mobile manipulation with egocentric human data? Meet EMMA: Egocentric Mobile MAnipulation EMMA learns from human mobile manipulation + static robot data — no mobile teleop needed! EMMA generalizes to new scenes and scales strongly with added human data. 1/9