Search papers, labs, and topics across Lattice.
7
0
8
3
Humanoid robots can learn entirely new complex manipulation skills at test-time by evolving reward programs, unlocking latent capabilities of pre-trained controllers.
Iterative image retrieval can now adapt contextually, achieving a 44.1 R@1 on multi-turn searches鈥攆ar surpassing previous benchmarks.
AniGS transforms static 3D reconstructions into dynamic, immersive environments by seamlessly integrating ambient motion without compromising structural fidelity.
Achieving a 95.8% success rate in resolving self-collisions, PoseShield transforms how we handle human pose estimation under extreme articulations.
A single generalist model outperforms specialized systems, achieving over 35% improvement in real-world robotic task success.
LLMs can scalably annotate motion capture data to produce semantically rich descriptions of bimanual interactions, enabling higher-quality generation of dexterous hand motions.
Humanoids can now perform complex loco-manipulation tasks from egocentric vision and sparse goals, thanks to a unified controller trained without relying on predefined motion references at test time.
