Search papers, labs, and topics across Lattice.
5
0
7
LLM trading agents might seem profitable, but a new benchmark reveals their returns are mostly just riding market trends, not actual stock-picking skill.
Musculoskeletal robots can achieve significantly better locomotion by co-designing morphology and control, simultaneously optimizing muscle strength, velocity, and stiffness, rather than relying on fixed physiological parameters.
Soft robots get a serious performance boost when you stop treating material stiffness as a fixed choice and start optimizing it continuously alongside shape and control.
Ditch brittle point-guided line matching: this VIO system uses optimal transport on learned line descriptors for globally consistent correspondences, boosting robustness in challenging visual conditions.
Musculoskeletal robots can now play table tennis, thanks to a hierarchical RL approach that cleverly sidesteps the curse of high-dimensional muscle control.
