Search papers, labs, and topics across Lattice.
5
0
5
2
Achieving 99.1% accuracy in object manipulation without the need for depth or additional 3D modules could revolutionize how robots interact with complex environments.
Hierarchical latent actions in HiMem-WAM boost long-horizon manipulation robustness, outperforming existing models in real-world scenarios.
Real-world robots forget how to fold towels after learning to pick-and-place, but this work shows experience replay can help, if you do it right.
By explicitly modeling spatial interaction and manipulation intent, AIM achieves a 94% success rate on RoboTwin 2.0, suggesting that robot control can be drastically improved by explicitly reasoning about *where* to interact, not just *how* scenes evolve.
Stop struggling with compounding errors in long-horizon robotic tasks: AtomVLA leverages LLMs and latent world models to decompose tasks and score actions, boosting success rates to 97% on LIBERO.
